tirana-indonesian-emotion
Query: Indonesian emotion detection RoBERTa IndoBERT
Results: 50
Date: 2026-07-08T07:34:50.567Z
1. Benchmarking PyCaret AutoML Against IndoBERT Fine-Tuning for Sentiment Analysis on Indonesian IKN Twitter Data
Authors: Mutia Alfi Mayzaroh, Dwi Fitria Ningsih, Nindi Destriani, Martin C. T. Manullang
Categories: cs.CL
Published: 2026-04-28
arXiv: 2604.25392v1
Abstract:
This paper benchmarks a classical machine learning approach based on PyCaret AutoML against a deep learning approach based on IndoBERT fine-tuning for binary sentiment analysis of Indonesian-language Twitter comments related to Ibu Kota Nusantara (IKN). The dataset contains 1,472 manually labeled samples, consisting of 780 negative and 692 positive comments. In the machine learning setting, Logistic Regression, Naive Bayes, and Support Vector Machine were evaluated using 10-fold cross-validation, with Logistic Regression achieving the best performance among the classical models at 77.57% accuracy and 77.17% F1-score. In the deep learning setting, the indobenchmark/indobert-base-p1 model was fine-tuned for five epochs and achieved 89.59% test accuracy and 89.37% F1-score. The results show that IndoBERT substantially outperforms the machine learning baselines, highlighting the effectiveness of Transformer-based contextual representations for informal Indonesian social media text.
2. Leveraging IndoBERT and DistilBERT for Indonesian Emotion Classification in E-Commerce Reviews
Authors: William Christian, Daniel Adamlu, Adrian Yu, Derwin Suhartono
Categories: cs.CL
Published: 2025-09-18
arXiv: 2509.14611v1
Abstract:
Understanding emotions in the Indonesian language is essential for improving customer experiences in e-commerce. This study focuses on enhancing the accuracy of emotion classification in Indonesian by leveraging advanced language models, IndoBERT and DistilBERT. A key component of our approach was data processing, specifically data augmentation, which included techniques such as back-translation and synonym replacement. These methods played a significant role in boosting the model’s performance. After hyperparameter tuning, IndoBERT achieved an accuracy of 80%, demonstrating the impact of careful data processing. While combining multiple IndoBERT models led to a slight improvement, it did not significantly enhance performance. Our findings indicate that IndoBERT was the most effective model for emotion classification in Indonesian, with data augmentation proving to be a vital factor in achieving high accuracy. Future research should focus on exploring alternative architectures and strategies to improve generalization for Indonesian NLP tasks.
3. Benchmarking Logistic Regression, SVM, Naive Bayes, and IndoBERT Fine-Tuning for Sentiment Analysis on Indonesian Product Reviews
Authors: Nabila Zakiyah Zahra, Salwa Farhanatussaidah, Nasywa Nur Afifah, Luluk Muthoharoh, Ardika Satria, Martin C. T. Manullang
Categories: cs.CL
Published: 2026-05-05
arXiv: 2605.03439v1
Abstract:
The exponential growth of e-commerce platforms in Indonesia has generated a massive volume of user-generated product reviews. Analyzing the sentiment of these reviews is critical for measuring customer satisfaction and identifying product issues at scale. This paper benchmarks traditional Machine Learning (ML) approaches against a Transformer-based Deep Learning model for a three-class sentiment analysis task (positive, neutral, negative) on the Tokopedia Product Reviews 2025 dataset. We implemented Term Frequency-Inverse Document Frequency (TF-IDF) feature extraction coupled with three algorithms: Logistic Regression, Linear Support Vector Machine (SVM), and Multinomial Naive Bayes as robust baselines. Subsequently, we fine-tuned the IndoBERT model (indobenchmark/indobert-base-p1) for contextual sequence classification. To computationally address the severe class imbalance inherent in e-commerce feedback, we applied balanced class weights for the baseline models and engineered a custom weighted cross-entropy loss function within the IndoBERT training loop, following the broader motivation of imbalanced-learning research. Our comprehensive evaluation using Accuracy, Macro F1-score, and Weighted F1-score revealed that the traditional Linear SVC model significantly outperformed the IndoBERT model in our experimental setup, achieving an Accuracy of 97.60% and a Macro F1-score of 0.5510, compared to IndoBERT’s 88.70% and 0.5088. Detailed analysis indicates that this performance gap was primarily driven by discrepancies in the data sampling regimes, where baselines utilized the full corpus while the Transformer was constrained to a sampled subset. Finally, we demonstrate the practical viability of our pipeline by deploying the final sentiment classification model as an interactive Gradio web application.
4. Sentiment Analysis: Automatically Detecting Valence, Emotions, and Other Affectual States from Text
Authors: Saif M. Mohammad
Categories: cs.CL
Published: 2020-05-25
arXiv: 2005.11882v2
Abstract:
Recent advances in machine learning have led to computer systems that are human-like in behaviour. Sentiment analysis, the automatic determination of emotions in text, is allowing us to capitalize on substantial previously unattainable opportunities in commerce, public health, government policy, social sciences, and art. Further, analysis of emotions in text, from news to social media posts, is improving our understanding of not just how people convey emotions through language but also how emotions shape our behaviour. This article presents a sweeping overview of sentiment analysis research that includes: the origins of the field, the rich landscape of tasks, challenges, a survey of the methods and resources used, and applications. We also discuss discuss how, without careful fore-thought, sentiment analysis has the potential for harmful outcomes. We outline the latest lines of research in pursuit of fairness in sentiment analysis.
5. Web-based Application for Detecting Indonesian Clickbait Headlines using IndoBERT
Authors: Muhammad Noor Fakhruzzaman, Sie Wildan Gunawan
Categories: cs.CL, cs.AI
Published: 2021-02-21
arXiv: 2102.10601v1
Abstract:
With increasing usage of clickbaits in Indonesian Online News, newsworthy articles sometimes get buried among clickbaity news. A reliable and lightweight tool is needed to detect such clickbaits on-the-go. Leveraging state-of-the-art natural language processing model BERT, a RESTful API based application is developed. This study offloaded the computing resources needed to train the model on the cloud server, while the client-side application only needs to send a request to the API and the cloud server will handle the rest. This study proposed the design and developed a web-based application to detect clickbait in Indonesian using IndoBERT as a language model. The application usage is discussed and available for public use with a performance of mean ROC-AUC of 89%.
6. IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP
Authors: Fajri Koto, Afshin Rahimi, Jey Han Lau, Timothy Baldwin
Categories: cs.CL
Published: 2020-11-02
arXiv: 2011.00677v1
Abstract:
Although the Indonesian language is spoken by almost 200 million people and the 10th most spoken language in the world, it is under-represented in NLP research. Previous work on Indonesian has been hampered by a lack of annotated datasets, a sparsity of language resources, and a lack of resource standardization. In this work, we release the IndoLEM dataset comprising seven tasks for the Indonesian language, spanning morpho-syntax, semantics, and discourse. We additionally release IndoBERT, a new pre-trained language model for Indonesian, and evaluate it over IndoLEM, in addition to benchmarking it against existing resources. Our experiments show that IndoBERT achieves state-of-the-art performance over most of the tasks in IndoLEM.
7. Comparative Analysis of AutoML and BiLSTM Models for Cyberbullying Detection on Indonesian Instagram Comments
Authors: Raihana Adelia Putri, Aisyah Musfirah, Anggi Puspita Ningrum, Luluk Muthoharoh, Ardika Satria, Martin Clinton Tosima Manullang
Categories: cs.CL
Published: 2026-04-29
arXiv: 2604.26229v1
Abstract:
This study compares machine learning and deep learning approaches for cyberbullying detection in Indonesian-language Instagram comments. Using a balanced dataset of 650 comments labeled as Bullying and Non-Bullying, the study evaluates Naive Bayes, Logistic Regression, and Support Vector Machine with TF-IDF features, as well as BiLSTM and BiLSTM with Bahdanau Attention. A preprocessing pipeline tailored to informal Indonesian text is applied, including slang normalization, stopword removal, and stemming. The results show that Logistic Regression performs best among the machine learning models, while BiLSTM with Attention achieves the strongest overall deep learning performance. The findings highlight the value of domain-specific preprocessing and show that although deep learning captures contextual patterns more effectively, machine learning remains a competitive option for resource-constrained deployments.
8. IndoBERT-Sentiment: Context-Conditioned Sentiment Classification for Indonesian Text
Authors: Muhammad Apriandito Arya Saputra, Andry Alamsyah, Dian Puteri Ramadhani, Thomhert Suprapto Siadari, Hanif Fakhrurroja
Categories: cs.CL
Published: 2026-04-08
arXiv: 2604.07057v1
Abstract:
Existing Indonesian sentiment analysis models classify text in isolation, ignoring the topical context that often determines whether a statement is positive, negative, or neutral. We introduce IndoBERT-Sentiment, a context-conditioned sentiment classifier that takes both a topical context and a text as input, producing sentiment predictions grounded in the topic being discussed. Built on IndoBERT Large (335M parameters) and trained on 31,360 context-text pairs labeled across 188 topics, the model achieves an F1 macro of 0.856 and accuracy of 88.1%. In a head-to-head evaluation against three widely used general-purpose Indonesian sentiment models on the same test set, IndoBERT-Sentiment outperforms the best baseline by 35.6 F1 points. We show that context-conditioning, previously demonstrated for relevancy classification, transfers effectively to sentiment analysis and enables the model to correctly classify texts that are systematically misclassified by context-free approaches.
9. Performance Evaluation of Emotion Classification in Japanese Using RoBERTa and DeBERTa
Authors: Yoichi Takenaka
Categories: cs.CL, cs.AI
Published: 2025-04-22
arXiv: 2505.00013v1
Abstract:
Background Practical applications such as social media monitoring and customer-feedback analysis require accurate emotion detection for Japanese text, yet resource scarcity and class imbalance hinder model performance. Objective This study aims to build a high-accuracy model for predicting the presence or absence of eight Plutchik emotions in Japanese sentences. Methods Using the WRIME corpus, we transform reader-averaged intensity scores into binary labels and fine-tune four pre-trained language models (BERT, RoBERTa, DeBERTa-v3-base, DeBERTa-v3-large). For context, we also assess two large language models (TinySwallow-1.5B-Instruct and ChatGPT-4o). Accuracy and F1-score serve as evaluation metrics. Results DeBERTa-v3-large attains the best mean accuracy (0.860) and F1-score (0.662), outperforming all other models. It maintains robust F1 across both high-frequency emotions (e.g., Joy, Anticipation) and low-frequency emotions (e.g., Anger, Trust). The LLMs lag, with ChatGPT-4o and TinySwallow-1.5B-Instruct scoring 0.527 and 0.292 in mean F1, respectively. Conclusion The fine-tuned DeBERTa-v3-large model currently offers the most reliable solution for binary emotion classification in Japanese. We release this model as a pip-installable package (pip install deberta-emotion-predictor). Future work should augment data for rare emotions, reduce model size, and explore prompt engineering to improve LLM performance. This manuscript is under review for possible publication in New Generation Computing.
10. IndoBERT-Relevancy: A Context-Conditioned Relevancy Classifier for Indonesian Text
Authors: Muhammad Apriandito Arya Saputra, Andry Alamsyah, Dian Puteri Ramadhani, Thomhert Suprapto Siadari, Hanif Fakhrurroja
Categories: cs.CL
Published: 2026-03-27
arXiv: 2603.26095v1
Abstract:
Determining whether a piece of text is relevant to a given topic is a fundamental task in natural language processing, yet it remains largely unexplored for Bahasa Indonesia. Unlike sentiment analysis or named entity recognition, relevancy classification requires the model to reason about the relationship between two inputs simultaneously: a topical context and a candidate text. We introduce IndoBERT-Relevancy, a context-conditioned relevancy classifier built on IndoBERT Large (335M parameters) and trained on a novel dataset of 31,360 labeled pairs spanning 188 topics. Through an iterative, failure-driven data construction process, we demonstrate that no single data source is sufficient for robust relevancy classification, and that targeted synthetic data can effectively address specific model weaknesses. Our final model achieves an F1 score of 0.948 and an accuracy of 96.5%, handling both formal and informal Indonesian text. The model is publicly available at HuggingFace.
11. General Purpose Textual Sentiment Analysis and Emotion Detection Tools
Authors: Alexandre Denis, Samuel Cruz-Lara, Nadia Bellalem
Categories: cs.CL
Published: 2013-09-11
arXiv: 1309.2853v1
Abstract:
Textual sentiment analysis and emotion detection consists in retrieving the sentiment or emotion carried by a text or document. This task can be useful in many domains: opinion mining, prediction, feedbacks, etc. However, building a general purpose tool for doing sentiment analysis and emotion detection raises a number of issues, theoretical issues like the dependence to the domain or to the language but also pratical issues like the emotion representation for interoperability. In this paper we present our sentiment/emotion analysis tools, the way we propose to circumvent the di culties and the applications they are used for.
12. Suryakala-Nusantara: Documenting Indonesian Sundials
Authors: Rhorom Priyatikanto
Categories: physics.pop-ph, astro-ph.IM
Published: 2013-12-10
arXiv: 1312.2742v1
Abstract:
Sundial is the ancient or classic timekeeper device, especially prior to the invention of mechanical clock. In the classical Islamic civilization, the daily movement of the Sun becomes main indicator of praying time, which can be deduced using sundial. This kind of device probably permeated to Indonesia during the Islamic acculturation. Since then, the development of astronomical knowledge, technology, art and architectural in classical Indonesia are partially reflected into sundial. These historical attractions of sundial demand comprehensive documentation and investigation of Indonesian sundial which are rarely found in the current literatures. The required spatial and temporal information regarding Indonesian sundial can be collected by general public through citizen science scheme. This concept may answer scientific curiosity of a research and also educate the people, expose them with science. In this article, general scheme of citizen science are discussed, its application for sundial study in Indonesia is proposed as Suryakala-Nusantara program.
13. Domain Adaptation of the Pyannote Diarization Pipeline for Conversational Indonesian Audio
Authors: Muhammad Daffa’i Rafi Prasetyo, Ramadhan Andika Putra, Zaidan Naufal Ilmi, Kurniawati Azizah
Categories: cs.SD
Published: 2026-01-07
arXiv: 2601.03684v1
Abstract:
This study presents a domain adaptation approach for speaker diarization targeting conversational Indonesian audio. We address the challenge of adapting an English-centric diarization pipeline to a low-resource language by employing synthetic data generation using neural Text-to-Speech technology. Experiments were conducted with varying training configurations, a small dataset (171 samples) and a large dataset containing 25 hours of synthetic speech. Results demonstrate that the baseline \texttt{pyannote/segmentation-3.0} model, trained on the AMI Corpus, achieves a Diarization Error Rate (DER) of 53.47% when applied zero-shot to Indonesian. Domain adaptation significantly improves performance, with the small dataset models reducing DER to 34.31% (1 epoch) and 34.81% (2 epochs). The model trained on the 25-hour dataset achieves the best performance with a DER of 29.24%, representing a 13.68% absolute improvement over the baseline while maintaining 99.06% Recall and 87.14% F1-Score.
14. A Comparative Study of PyCaret AutoML and CNN-BiLSTM for Binary Hate Speech Detection in Indonesian Twitter
Authors: Tanty Widiyastuti, Mayada, Adisty Syawalda Ariyanto, Luluk Muthoharoh, Ardika Satria, Martin Clinton Tosima Manullang
Categories: cs.CL
Published: 2026-05-06
arXiv: 2605.04885v1
Abstract:
This paper compares a PyCaret AutoML branch and a CNN-BiLSTM branch for binary hate speech detection on Indonesian Twitter using the HS label from the corpus of Ibrohim and Budi. Both branches share the same preprocessing pipeline so that the comparison reflects modelling differences rather than inconsistent data preparation. The conventional branch uses TF-IDF with a lexicon-based abusive-word count, whereas the neural branch learns dense token representations and captures both local phrase patterns and bidirectional context. The benchmark is built from the released 13,130-row annotation table, whose HS label yields a 58:42 class ratio. On the held-out split, CNN-BiLSTM achieves the best result with 83.8% accuracy, 79.8% precision, 82.7% recall, and 81.2% F1-score. Within the PyCaret branch, Random Forest is the strongest conventional model with 77.2% accuracy and 77.0% F1-score. The neural branch therefore improves accuracy by 6.6 points and F1-score by 4.2 points. Exploratory corpus analysis, learning curves, and confusion matrices show that the dataset is short-text, moderately imbalanced, and still difficult because many decisions depend on local lexical cues plus short contextual composition. The study concludes that PyCaret AutoML is an effective conventional benchmarking framework, whereas CNN-BiLSTM is the stronger end model for the reported benchmark setting.
15. OmniMER: Auxiliary-Enhanced LLM Adaptation for Indonesian Multimodal Emotion Recognition
Authors: Xueming Yan, Boyan Xu, Yaochu Jin, Lixian Xiao, Wenlong Ye, Runyang Cai, Zeqi Zheng, Jingfa Liu, Aimin Yang, Yongduan Song
Categories: cs.LG, cs.AI, cs.MM
Published: 2025-12-22
arXiv: 2512.19379v3
Abstract:
Indonesian, spoken by over 200 million people, remains underserved in multimodal emotion recognition research despite its dominant presence on Southeast Asian social media platforms. We introduce IndoMER, the first multimodal emotion recognition benchmark for Indonesian, comprising 1,944 video segments from 203 speakers with temporally aligned text, audio, and visual annotations across seven emotion categories. The dataset exhibits realistic challenges including cross-modal inconsistency and long-tailed class distributions shaped by Indonesian cultural communication norms. To address these challenges, we propose OmniMER, a multimodal adaptation framework built upon Qwen2.5-Omni that enhances emotion recognition through three auxiliary modality-specific perception tasks: emotion keyword extraction for text, facial expression analysis for video, and prosody analysis for audio. These auxiliary tasks help the model identify emotion-relevant cues in each modality before fusion, reducing reliance on spurious correlations in low-resource settings. Experiments on IndoMER show that OmniMER achieves 0.582 Macro-F1 on sentiment classification and 0.454 on emotion recognition, outperforming the base model by 7.6 and 22.1 absolute points respectively. Cross-lingual evaluation on the Chinese CH-SIMS dataset further demonstrates the generalizability of the proposed framework. The dataset and code are publicly available. https://github.com/yanxm01/INDOMER
16. PO-EMO: Conceptualization, Annotation, and Modeling of Aesthetic Emotions in German and English Poetry
Authors: Thomas Haider, Steffen Eger, Evgeny Kim, Roman Klinger, Winfried Menninghaus
Categories: cs.CL
Published: 2020-03-17
arXiv: 2003.07723v3
Abstract:
Most approaches to emotion analysis of social media, literature, news, and other domains focus exclusively on basic emotion categories as defined by Ekman or Plutchik. However, art (such as literature) enables engagement in a broader range of more complex and subtle emotions. These have been shown to also include mixed emotional responses. We consider emotions in poetry as they are elicited in the reader, rather than what is expressed in the text or intended by the author. Thus, we conceptualize a set of aesthetic emotions that are predictive of aesthetic appreciation in the reader, and allow the annotation of multiple labels per line to capture mixed emotions within their context. We evaluate this novel setting in an annotation experiment both with carefully trained experts and via crowdsourcing. Our annotation with experts leads to an acceptable agreement of kappa = .70, resulting in a consistent dataset for future large scale analysis. Finally, we conduct first emotion classification experiments based on BERT, showing that identifying aesthetic emotions is challenging in our data, with up to .52 F1-micro on the German subset. Data and resources are available at https://github.com/tnhaider/poetry-emotion
17. Hybrid TF–IDF Logistic Regression and MLP Neural Baseline for Indonesian Three-Class Sentiment Analysis on Social Media Text
Authors: Allya Nurul Islami Pasha, Eka Fidiya Putri, Luluk Muthoharoh, Ardika Satria, Martin C. T. Manullang
Categories: cs.CL
Published: 2026-05-08
arXiv: 2605.07793v1
Abstract:
This paper presents a compact three-class sentiment analysis study for Indonesian social media text. The task is formulated with positive, negative, and neutral outputs derived from a fine-grained emotion dataset. The proposed practical baseline combines TF–IDF text features, three lightweight numeric metadata features, and a balanced multinomial Logistic Regression classifier. For comparison, the study also includes a neural baseline using a two-layer multilayer perceptron (MLP) over the same hybrid feature representation. The dataset originally contains 732 rows and 191 fine-grained emotion labels; after cleaning, deduplication, and label remapping, 707 samples remain with an imbalanced distribution of 459 positive, 188 negative, and 60 neutral instances. Experimental results show that the Logistic Regression deployment model reaches 0.8028 accuracy, 0.8003 weighted F1, and 0.7276 macro F1, while project documentation reports a higher-accuracy but non-production MLP baseline. These findings indicate that careful preprocessing, interpretable feature engineering, and class balancing remain competitive for small Indonesian sentiment datasets, whereas the neural baseline is better treated as a comparative experiment than as the default deployment model.
18. MICE: A Crosslinguistic Emotion Corpus in Malay, Indonesian, Chinese and English
Authors: Ng Bee Chin, Yosephine Susanto, Erik Cambria
Categories: cs.CL
Published: 2021-06-09
arXiv: 2106.04831v1
Abstract:
MICE is a corpus of emotion words in four languages which is currently working progress. There are two sections to this study, Part I: Emotion word corpus and Part II: Emotion word survey. In Part 1, the method of how the emotion data is culled for each of the four languages will be described and very preliminary data will be presented. In total, we identified 3,750 emotion expressions in Malay, 6,657 in Indonesian, 3,347 in Mandarin Chinese and 8,683 in English. We are currently evaluating and double checking the corpus and doing further analysis on the distribution of these emotion expressions. Part II Emotion word survey involved an online language survey which collected information on how speakers assigned the emotion words into basic emotion categories, the rating for valence and intensity as well as biographical information of all the respondents.
19. Continuous Learning Based Novelty Aware Emotion Recognition System
Authors: Mijanur Palash, Bharat Bhargava
Categories: cs.CV, cs.LG, cs.MM
Published: 2023-06-14
arXiv: 2306.08733v1
Abstract:
Current works in human emotion recognition follow the traditional closed learning approach governed by rigid rules without any consideration of novelty. Classification models are trained on some collected datasets and expected to have the same data distribution in the real-world deployment. Due to the fluid and constantly changing nature of the world we live in, it is possible to have unexpected and novel sample distribution which can lead the model to fail. Hence, in this work, we propose a continuous learning based approach to deal with novelty in the automatic emotion recognition task.
20. Contextual Emotion Estimation from Image Captions
Authors: Vera Yang, Archita Srivastava, Yasaman Etesam, Chuxuan Zhang, Angelica Lim
Categories: cs.CV, cs.AI
Published: 2023-09-22
arXiv: 2309.13136v1
Abstract:
Emotion estimation in images is a challenging task, typically using computer vision methods to directly estimate people’s emotions using face, body pose and contextual cues. In this paper, we explore whether Large Language Models (LLMs) can support the contextual emotion estimation task, by first captioning images, then using an LLM for inference. First, we must understand: how well do LLMs perceive human emotions? And which parts of the information enable them to determine emotions? One initial challenge is to construct a caption that describes a person within a scene with information relevant for emotion perception. Towards this goal, we propose a set of natural language descriptors for faces, bodies, interactions, and environments. We use them to manually generate captions and emotion annotations for a subset of 331 images from the EMOTIC dataset. These captions offer an interpretable representation for emotion estimation, towards understanding how elements of a scene affect emotion perception in LLMs and beyond. Secondly, we test the capability of a large language model to infer an emotion from the resulting image captions. We find that GPT-3.5, specifically the text-davinci-003 model, provides surprisingly reasonable emotion predictions consistent with human annotations, but accuracy can depend on the emotion concept. Overall, the results suggest promise in the image captioning and LLM approach.
21. Towards Indonesian Speech-Emotion Automatic Recognition (I-SpEAR)
Authors: Novita Belinda Wunarso, Yustinus Eko Soelistio
Categories: cs.HC
Published: 2017-09-25
arXiv: 1709.10460v1
Abstract:
Even though speech-emotion recognition (SER) has been receiving much attention as research topic, there are still some disputes about which vocal features can identify certain emotion. Emotion expression is also known to be differed according to the cultural backgrounds that make it important to study SER specific to the culture where the language belongs to. Furthermore, only a few studies addresses the SER in Indonesian which what this study attempts to explore. In this study, we extract simple features from 3420 voice data gathered from 38 participants. The features are compared by means of linear mixed effect model which shows that people who are in emotional and non-emotional state can be differentiated by their speech duration. Using SVM and speech duration as input feature, we achieve 76.84% average accuracy in classifying emotional and non-emotional speech.
22. Benchmarking LightGBM and BiLSTM for Sentiment Analysis on Indonesian E-Commerce Reviews
Authors: Lidia Natasyah Marpaung, Vania Claresta, Iqfina Haula Halika, Luluk Muthoharoh, Ardika Satria, Martin Clinton Tosima Manullang
Categories: cs.CL
Published: 2026-05-02
arXiv: 2605.01322v1
Abstract:
This study presents a comparative analysis between two primary approaches in Natural Language Processing (NLP): Machine Learning (ML) utilizing the PyCaret AutoML framework, and Deep Learning (DL). The evaluation is conducted on a sentiment analysis task using an Indonesian e-commerce review dataset sourced from Hugging Face. The dataset, consisting of 15,000 samples, is partitioned into training, validation, and testing sets. The ML experiments compare LightGBM, Logistic Regression, and Support Vector Machine (SVM) algorithms, whereas the DL experiment implements a Bidirectional Long Short-Term Memory (BiLSTM) architecture. The experimental results demonstrate that the BiLSTM model outperforms all ML models, achieving an accuracy of 98.87% and an F1-Score of 98.87%. Meanwhile, LightGBM emerges as the best-performing ML model with an accuracy of 98.23% in a highly efficient training time. This research proves that the BiLSTM architecture is highly capable of capturing the sequential context of Indonesian review texts, making it the superior model for this specific classification task.
23. Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning
Authors: Zebang Cheng, Zhi-Qi Cheng, Jun-Yan He, Jingdong Sun, Kai Wang, Yuxiang Lin, Zheng Lian, Xiaojiang Peng, Alexander Hauptmann
Categories: cs.AI, cs.MM
Published: 2024-06-17
arXiv: 2406.11161v2
Abstract:
Accurate emotion perception is crucial for various applications, including human-computer interaction, education, and counseling. However, traditional single-modality approaches often fail to capture the complexity of real-world emotional expressions, which are inherently multimodal. Moreover, existing Multimodal Large Language Models (MLLMs) face challenges in integrating audio and recognizing subtle facial micro-expressions. To address this, we introduce the MERR dataset, containing 28,618 coarse-grained and 4,487 fine-grained annotated samples across diverse emotional categories. This dataset enables models to learn from varied scenarios and generalize to real-world applications. Furthermore, we propose Emotion-LLaMA, a model that seamlessly integrates audio, visual, and textual inputs through emotion-specific encoders. By aligning features into a shared space and employing a modified LLaMA model with instruction tuning, Emotion-LLaMA significantly enhances both emotional recognition and reasoning capabilities. Extensive evaluations show Emotion-LLaMA outperforms other MLLMs, achieving top scores in Clue Overlap (7.83) and Label Overlap (6.25) on EMER, an F1 score of 0.9036 on MER2023-SEMI challenge, and the highest UAR (45.59) and WAR (59.37) in zero-shot evaluations on DFEW dataset.
24. Enhancing Student Engagement in Online Learning through Facial Expression Analysis and Complex Emotion Recognition using Deep Learning
Authors: Rekha R Nair, Tina Babu, Pavithra K
Categories: cs.CV
Published: 2023-11-17
arXiv: 2311.10343v1
Abstract:
In response to the COVID-19 pandemic, traditional physical classrooms have transitioned to online environments, necessitating effective strategies to ensure sustained student engagement. A significant challenge in online teaching is the absence of real-time feedback from teachers on students learning progress. This paper introduces a novel approach employing deep learning techniques based on facial expressions to assess students engagement levels during online learning sessions. Human emotions cannot be adequately conveyed by a student using only the basic emotions, including anger, disgust, fear, joy, sadness, surprise, and neutrality. To address this challenge, proposed a generation of four complex emotions such as confusion, satisfaction, disappointment, and frustration by combining the basic emotions. These complex emotions are often experienced simultaneously by students during the learning session. To depict these emotions dynamically,utilized a continuous stream of image frames instead of discrete images. The proposed work utilized a Convolutional Neural Network (CNN) model to categorize the fundamental emotional states of learners accurately. The proposed CNN model demonstrates strong performance, achieving a 95% accuracy in precise categorization of learner emotions.
25. EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa
Authors: Taewoon Kim, Piek Vossen
Categories: cs.CL
Published: 2021-08-26
arXiv: 2108.12009v1
Abstract:
We present EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa, a simple yet expressive scheme of solving the ERC (emotion recognition in conversation) task. By simply prepending speaker names to utterances and inserting separation tokens between the utterances in a dialogue, EmoBERTa can learn intra- and inter- speaker states and context to predict the emotion of a current speaker, in an end-to-end manner. Our experiments show that we reach a new state of the art on the two popular ERC datasets using a basic and straight-forward approach. We’ve open sourced our code and models at https://github.com/tae898/erc.
26. The Relationship Between Emotion Models and Artificial Intelligence
Authors: Christoph Bartneck, Michael J. Lyons, Martin Saerbeck
Categories: cs.HC
Published: 2017-06-29
arXiv: 1706.09554v1
Abstract:
Emotions play a central role in most forms of natural human interaction so we may expect that computational methods for the processing and expression of emotions will play a growing role in human-computer interaction. The OCC model has established itself as the standard model for emotion synthesis. A large number of studies employed the OCC model to generate emotions for their embodied characters. Many developers of such characters believe that the OCC model will be all they ever need to equip their character with emotions. This study reflects on the limitations of the OCC model specifically, and on the emotion models in general due to their dependency on artificial intelligence.
27. Exploring Transformers in Emotion Recognition: a comparison of BERT, DistillBERT, RoBERTa, XLNet and ELECTRA
Authors: Diogo Cortiz
Categories: cs.CL
Published: 2021-04-05
arXiv: 2104.02041v1
Abstract:
This paper investigates how Natural Language Understanding (NLU) could be applied in Emotion Recognition, a specific task in affective computing. We finetuned different transformers language models (BERT, DistilBERT, RoBERTa, XLNet, and ELECTRA) using a fine-grained emotion dataset and evaluating them in terms of performance (f1-score) and time to complete.
28. Towards Emotion-Based Synthetic Consciousness: Using LLMs to Estimate Emotion Probability Vectors
Authors: David Sinclair, Willem Pye
Categories: cs.CL
Published: 2023-10-09
arXiv: 2310.10673v1
Abstract:
This paper shows how LLMs (Large Language Models) may be used to estimate a summary of the emotional state associated with piece of text. The summary of emotional state is a dictionary of words used to describe emotion together with the probability of the word appearing after a prompt comprising the original text and an emotion eliciting tail. Through emotion analysis of Amazon product reviews we demonstrate emotion descriptors can be mapped into a PCA type space. It was hoped that text descriptions of actions to improve a current text described state could also be elicited through a tail prompt. Experiment seemed to indicate that this is not straightforward to make work. This failure put our hoped for selection of action via choosing the best predict ed outcome via comparing emotional responses out of reach for the moment.
29. Edge Based Grid Super-Imposition for Crowd Emotion Recognition
Authors: Amol Patwardhan
Categories: cs.CV, cs.HC
Published: 2016-08-07
arXiv: 1610.05566v1
Abstract:
Numerous automatic continuous emotion detection system studies have examined mostly use of videos and images containing individual person expressing emotions. This study examines the detection of spontaneous emotions in a group and crowd settings. Edge detection was used with a grid of lines superimposition to extract the features. The feature movement in terms of movement from the reference point was used to track across sequences of images from the color channel. Additionally the video data capturing was done on spontaneous emotions invoked by watching sports events from group of participants. The method was view and occlusion independent and the results were not affected by presence of multiple people chaotically expressing various emotions. The edge thresholds of 0.2 and grid thresholds of 20 showed the best accuracy results. The overall accuracy of the group emotion classifier was 70.9%.
30. Emotion Recognition in the Wild using Deep Neural Networks and Bayesian Classifiers
Authors: Luca Surace, Massimiliano Patacchiola, Elena Battini Sönmez, William Spataro, Angelo Cangelosi
Categories: cs.CV
Published: 2017-09-12
arXiv: 1709.03820v1
Abstract:
Group emotion recognition in the wild is a challenging problem, due to the unstructured environments in which everyday life pictures are taken. Some of the obstacles for an effective classification are occlusions, variable lighting conditions, and image quality. In this work we present a solution based on a novel combination of deep neural networks and Bayesian classifiers. The neural network works on a bottom-up approach, analyzing emotions expressed by isolated faces. The Bayesian classifier estimates a global emotion integrating top-down features obtained through a scene descriptor. In order to validate the system we tested the framework on the dataset released for the Emotion Recognition in the Wild Challenge 2017. Our method achieved an accuracy of 64.68% on the test set, significantly outperforming the 53.62% competition baseline.
31. Domain-Specific Language Model Post-Training for Indonesian Financial NLP
Authors: Ni Putu Intan Maharani, Yoga Yustiawan, Fauzy Caesar Rochim, Ayu Purwarianti
Categories: cs.CL, cs.AI
Published: 2023-10-15
arXiv: 2310.09736v1
Abstract:
BERT and IndoBERT have achieved impressive performance in several NLP tasks. There has been several investigation on its adaption in specialized domains especially for English language. We focus on financial domain and Indonesian language, where we perform post-training on pre-trained IndoBERT for financial domain using a small scale of Indonesian financial corpus. In this paper, we construct an Indonesian self-supervised financial corpus, Indonesian financial sentiment analysis dataset, Indonesian financial topic classification dataset, and release a family of BERT models for financial NLP. We also evaluate the effectiveness of domain-specific post-training on sentiment analysis and topic classification tasks. Our findings indicate that the post-training increases the effectiveness of a language model when it is fine-tuned to domain-specific downstream tasks.
32. Lotus at SemEval-2025 Task 11: RoBERTa with Llama-3 Generated Explanations for Multi-Label Emotion Classification
Authors: Niloofar Ranjbar, Hamed Baghbani
Categories: cs.LG, cs.AI
Published: 2025-02-27
arXiv: 2502.19935v3
Abstract:
This paper presents a novel approach for multi-label emotion detection, where Llama-3 is used to generate explanatory content that clarifies ambiguous emotional expressions, thereby enhancing RoBERTa’s emotion classification performance. By incorporating explanatory context, our method improves F1-scores, particularly for emotions like fear, joy, and sadness, and outperforms text-only models. The addition of explanatory content helps resolve ambiguity, addresses challenges like overlapping emotional cues, and enhances multi-label classification, marking a significant advancement in emotion detection tasks.
33. Towards the Assessment of Stress and Emotional Responses of a Salutogenesis-Enhanced Software Tool Using Psychophysiological Measurements
Authors: Jan-Peter Ostberg, Daniel Graziotin, Stefan Wagner, Birgit Derntl
Categories: cs.SE, cs.CY, cs.HC
Published: 2017-01-20
arXiv: 1701.05739v2
Abstract:
Software development is intellectual, based on collaboration, and performed in a highly demanding economic market. As such, it is dominated by time pressure, stress, and emotional trauma. While studies of affect are emerging and rising in software engineering research, stress has yet to find its place in the literature despite that it is highly related to affect. In this paper, we study stress coping with the affect-laden framework of Salutogenesis, which is a validated psychological framework for enhancing mental health through a feeling of coherence. We propose a controlled experiment for testing our hypotheses that a static analysis tool enhanced with the Salutogenesis model will bring 1) a higher number of fixed quality issues, 2) reduced cognitive load, 3) reduction of the overall stress, and 4) positive affect induction effects to developers. The experiment will make use of validated physiological measurements of stress as proxied by cortisol and alpha-amylase levels in saliva samples, a psychometrically validated measurement of mood and affect disposition, and stress inductors such as a cognitive load task. Our hypotheses, if empirically supported, will lead to the creation of environments, methods, and tools that alleviate stress among developers while enhancing affect on the job and task performance.
34. Current Challenges of Using Wearable Devices for Online Emotion Sensing
Authors: Weiwei Jiang, Kangning Yang, Maximiliane Windl, Francesco Chiossi, Benjamin Tag, Sven Mayer, Zhanna Sarsenbayeva
Categories: cs.HC
Published: 2022-08-10
arXiv: 2208.05206v1
Abstract:
A growing number of wearable devices is becoming increasingly non-invasive, readily available, and versatile for measuring different physiological signals. This renders them ideal for inferring the emotional states of their users. Despite the success of wearable devices in recent emotion studies, there are still several challenges to be addressed. In this position paper, we compare currently available wearables that can be used for emotion-sensing and identify the challenges and opportunities for future researchers. Our investigation opens the discussion of what is missing for in-the-wild for emotion-sensing studies.
35. Sentiment Analysis of Indonesian Spotify Reviews Using Machine Learning and BiLSTM
Authors: Uliano Wilyam Purba, Andre Hadiman Rotua Parhusip, Sahid Maulana, Luluk Muthoharoh, Ardika Satria, Martin C. T. Manullang
Categories: cs.CL
Published: 2026-05-05
arXiv: 2605.03443v1
Abstract:
This paper benchmarks classical machine learning and deep learning approaches for three-class sentiment classification of Indonesian Spotify reviews. Using 100,000 scraped reviews and 70,155 cleaned samples, the study compares Support Vector Machine, Multinomial Naive Bayes, and Decision Tree models with a two-layer BiLSTM. Both approaches use the same preprocessing pipeline, including slang normalization, stopword removal, and stemming. Decision Tree achieves the best performance among the classical models, while BiLSTM attains the highest weighted F1-score overall but fails on the minority neutral class. The paper concludes that BiLSTM is stronger for overall sentiment detection, whereas machine learning with SMOTE provides more balanced three-class performance.
36. EmoAtt at EmoInt-2017: Inner attention sentence embedding for Emotion Intensity
Authors: Edison Marrese-Taylor, Yutaka Matsuo
Categories: cs.CL
Published: 2017-08-18
arXiv: 1708.05521v1
Abstract:
In this paper we describe a deep learning system that has been designed and built for the WASSA 2017 Emotion Intensity Shared Task. We introduce a representation learning approach based on inner attention on top of an RNN. Results show that our model offers good capabilities and is able to successfully identify emotion-bearing words to predict intensity without leveraging on lexicons, obtaining the 13th place among 22 shared task competitors.
37. Best Practices in the Creation and Use of Emotion Lexicons
Authors: Saif M. Mohammad
Categories: cs.CL
Published: 2022-10-13
arXiv: 2210.07206v2
Abstract:
Words play a central role in how we express ourselves. Lexicons of word-emotion associations are widely used in research and real-world applications for sentiment analysis, tracking emotions associated with products and policies, studying health disorders, tracking emotional arcs of stories, and so on. However, inappropriate and incorrect use of these lexicons can lead to not just sub-optimal results, but also inferences that are directly harmful to people. This paper brings together ideas from Affective Computing and AI Ethics to present, some of the practical and ethical considerations involved in the creation and use of emotion lexicons – best practices. The goal is to provide a comprehensive set of relevant considerations, so that readers (especially those new to work with emotions) can find relevant information in one place. We hope this work will facilitate more thoughtfulness when one is deciding on what emotions to work on, how to create an emotion lexicon, how to use an emotion lexicon, how to draw meaningful inferences, and how to judge success.
38. Two-Stage Classifier for COVID-19 Misinformation Detection Using BERT: a Study on Indonesian Tweets
Authors: Douglas Raevan Faisal, Rahmad Mahendra
Categories: cs.CL, cs.SI
Published: 2022-06-30
arXiv: 2206.15359v1
Abstract:
The COVID-19 pandemic has caused globally significant impacts since the beginning of 2020. This brought a lot of confusion to society, especially due to the spread of misinformation through social media. Although there were already several studies related to the detection of misinformation in social media data, most studies focused on the English dataset. Research on COVID-19 misinformation detection in Indonesia is still scarce. Therefore, through this research, we collect and annotate datasets for Indonesian and build prediction models for detecting COVID-19 misinformation by considering the tweet’s relevance. The dataset construction is carried out by a team of annotators who labeled the relevance and misinformation of the tweet data. In this study, we propose the two-stage classifier model using IndoBERT pre-trained language model for the Tweet misinformation detection task. We also experiment with several other baseline models for text classification. The experimental results show that the combination of the BERT sequence classifier for relevance prediction and Bi-LSTM for misinformation detection outperformed other machine learning models with an accuracy of 87.02%. Overall, the BERT utilization contributes to the higher performance of most prediction models. We release a high-quality COVID-19 misinformation Tweet corpus in the Indonesian language, indicated by the high inter-annotator agreement.
39. Emo-LiPO: Listwise Preference Optimization for Fine-Grained Emotion Intensity Control in LLM-based Text-to-Speech
Authors: Yihang Lin, Li Zhou, Congwei Cao, Dongchu Xie, Xiaoxue Gao, Chen Zhang, Haizhou Li
Categories: cs.SD
Published: 2026-06-11
arXiv: 2606.13006v1
Abstract:
Large language model (LLM)-based text-to-speech (TTS) systems enable prompt-conditioned emotional control but struggle with fine-grained emotion intensity due to the semantic – acoustic gap between text and speech. To address this challenge, we formulate emotion intensity control in LLM-based TTS as a learning-to-rank problem and propose Emo-LiPO, a listwise preference optimization framework that aligns prompt-conditioned speech generation with relative emotion intensity expressed in text. Emo-LiPO explicitly models global intensity ordering within each emotion under fixed transcripts, enabling more faithful and continuous emotional expression. We further construct ESD-plus, a multi-speaker dataset with explicit emotion intensity variations, to support fine-grained emotion modeling and evaluation. Experiments on ESD-plus demonstrate that Emo-LiPO significantly improves emotion accuracy and intensity controllability over both supervised- and DPO-based LLM TTS baselines, with particularly pronounced gains at high intensity levels.
40. E-ICL: Enhancing Fine-Grained Emotion Recognition through the Lens of Prototype Theory
Authors: Zhaochun Ren, Zhou Yang, Chenglong Ye, Yufeng Wang, Haizhou Sun, Chao Chen, Xiaofei Zhu, Yunbing Wu, Xiangwen Liao
Categories: cs.LG, cs.AI
Published: 2024-06-04
arXiv: 2406.02642v4
Abstract:
In-context learning (ICL) achieves remarkable performance in various domains such as knowledge acquisition, commonsense reasoning, and semantic understanding. However, its performance significantly deteriorates for emotion detection tasks, especially fine-grained emotion recognition. The underlying reasons for this remain unclear. In this paper, we identify the reasons behind ICL’s poor performance from the perspective of prototype theory and propose a method to address this issue. Specifically, we conduct extensive pilot experiments and find that ICL conforms to the prototype theory on fine-grained emotion recognition. Based on this theory, we uncover the following deficiencies in ICL: (1) It relies on prototypes (example-label pairs) that are semantically similar but emotionally inaccurate to predict emotions. (2) It is prone to interference from irrelevant categories, affecting the accuracy and robustness of the predictions. To address these issues, we propose an Emotion Context Learning method (E-ICL) on fine-grained emotion recognition. E-ICL relies on more emotionally accurate prototypes to predict categories by referring to emotionally similar examples with dynamic labels. Simultaneously, E-ICL employs an exclusionary emotion prediction strategy to avoid interference from irrelevant categories, thereby increasing its accuracy and robustness. Note that the entire process is accomplished with the assistance of a plug-and-play emotion auxiliary model, without additional training. Experiments on the fine-grained emotion datasets EDOS, Empathetic-Dialogues, EmpatheticIntent, and GoEmotions show that E-ICL achieves superior emotion prediction performance. Furthermore, even when the emotion auxiliary model used is lower than 10% of the LLMs, E-ICL can still boost the performance of LLMs by over 4% on multiple datasets.
41. A Unified and Interpretable Emotion Representation and Expression Generation
Authors: Reni Paskaleva, Mykyta Holubakha, Andela Ilic, Saman Motamed, Luc Van Gool, Danda Paudel
Categories: cs.CV
Published: 2024-04-01
arXiv: 2404.01243v1
Abstract:
Canonical emotions, such as happy, sad, and fearful, are easy to understand and annotate. However, emotions are often compound, e.g. happily surprised, and can be mapped to the action units (AUs) used for expressing emotions, and trivially to the canonical ones. Intuitively, emotions are continuous as represented by the arousal-valence (AV) model. An interpretable unification of these four modalities - namely, Canonical, Compound, AUs, and AV - is highly desirable, for a better representation and understanding of emotions. However, such unification remains to be unknown in the current literature. In this work, we propose an interpretable and unified emotion model, referred as C2A2. We also develop a method that leverages labels of the non-unified models to annotate the novel unified one. Finally, we modify the text-conditional diffusion models to understand continuous numbers, which are then used to generate continuous expressions using our unified emotion model. Through quantitative and qualitative experiments, we show that our generated images are rich and capture subtle expressions. Our work allows a fine-grained generation of expressions in conjunction with other textual inputs and offers a new label space for emotions at the same time.
42. EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech Synthesis
Authors: Li Zhou, Hao Jiang, Junjie Li, Tianrui Wang, Haizhou Li
Categories: eess.AS, cs.AI, cs.CL, cs.SD
Published: 2026-01-30
arXiv: 2601.22873v1
Abstract:
Achieving precise and controllable emotional expression is crucial for producing natural and context-appropriate speech in text-to-speech (TTS) synthesis. However, many emotion-aware TTS systems, including large language model (LLM)-based designs, rely on scaling fixed emotion embeddings or external guidance, limiting their ability to model emotion-specific latent characteristics. To address this gap, we present EmoShift, a lightweight activation-steering framework incorporating a EmoSteer layer, which learns a steering vector for each target emotion in the output embedding space to capture its latent offset and maintain stable, appropriate expression across utterances and categories. With only 10M trainable parameters,less than 1/30 of full fine-tuning, EmoShift outperforms zero-shot and fully fine-tuned baselines in objective and subjective evaluations, enhancing emotional expressiveness while preserving naturalness and speaker similarity. Further analysis confirms the proposed EmoSteer layer’s effectiveness and reveals its potential for controllable emotional intensity in speech synthesis.
43. Emotion Understanding in Videos Through Body, Context, and Visual-Semantic Embedding Loss
Authors: Panagiotis Paraskevas Filntisis, Niki Efthymiou, Gerasimos Potamianos, Petros Maragos
Categories: cs.CV
Published: 2020-10-30
arXiv: 2010.16396v1
Abstract:
We present our winning submission to the First International Workshop on Bodily Expressed Emotion Understanding (BEEU) challenge. Based on recent literature on the effect of context/environment on emotion, as well as visual representations with semantic meaning using word embeddings, we extend the framework of Temporal Segment Network to accommodate these. Our method is verified on the validation set of the Body Language Dataset (BoLD) and achieves 0.26235 Emotion Recognition Score on the test set, surpassing the previous best result of 0.2530.
44. EMTk – The Emotion Mining Toolkit
Authors: Fabio Calefato, Filippo Lanubile, Nicole Novielli, Luigi Quaranta
Categories: cs.SE
Published: 2019-03-22
arXiv: 1903.09525v3
Abstract:
The Emotion Mining Toolkit (EMTk) is a suite of modules and datasets offering a comprehensive solution for mining sentiment and emotions from technical text contributed by developers on communication channels. The toolkit is written in Java, Python, and R, and is released under the MIT open source license. In this paper, we describe its architecture and the benchmark against the previous, standalone versions of our sentiment analysis tools. Results show large improvements in terms of speed.
45. Transformer-based Text Classification on Unified Bangla Multi-class Emotion Corpus
Authors: Md Sakib Ullah Sourav, Huidong Wang, Mohammad Sultan Mahmud, Hua Zheng
Categories: cs.CL
Published: 2022-10-12
arXiv: 2210.06405v3
Abstract:
In this research, we propose a complete set of approaches for identifying and extracting emotions from Bangla texts. We provide a Bangla emotion classifier for six classes: anger, disgust, fear, joy, sadness, and surprise, from Bangla words using transformer-based models, which exhibit phenomenal results in recent days, especially for high-resource languages. The Unified Bangla Multi-class Emotion Corpus (UBMEC) is used to assess the performance of our models. UBMEC is created by combining two previously released manually labeled datasets of Bangla comments on six emotion classes with fresh manually labeled Bangla comments created by us. The corpus dataset and code we used in this work are publicly available.
46. Detecting Botnets Through Log Correlation
Authors: Yousof Al-Hammadi, Uwe Aickelin
Categories: cs.AI, cs.CR
Published: 2010-01-15
arXiv: 1001.2665v1
Abstract:
Botnets, which consist of thousands of compromised machines, can cause significant threats to other systems by launching Distributed Denial of Service (SSoS) attacks, keylogging, and backdoors. In response to these threats, new effective techniques are needed to detect the presence of botnets. In this paper, we have used an interception technique to monitor Windows Application Programming Interface (API) functions calls made by communication applications and store these calls with their arguments in log files. Our algorithm detects botnets based on monitoring abnormal activity by correlating the changes in log file sizes from different hosts.
47. Single-point spin Chern number in a supercell framework
Authors: Roberta Favata, Antimo Marrazzo
Categories: cond-mat.mes-hall, cond-mat.mtrl-sci
Published: 2023-01-06
arXiv: 2301.02612v1
Abstract:
We present an approach for the calculation of the $\mathbb{Z}_2$ topological invariant in non-crystalline two-dimensional quantum spin Hall insulators. While topological invariants were originally mathematically introduced for crystalline periodic systems, and crucially hinge on tracking the evolution of occupied states through the Brillouin zone, the introduction of disorder or dynamical effects can break the translational symmetry and imply the use of larger simulation cells, where the $\bf{k}$-point sampling is typically reduced to the single $Γ$-point. Here, we introduce a single-point formula for the spin Chern number that enables to adopt the supercell framework, where a single Hamiltonian diagonalisation is performed. Inspired by the work of E. Prodan [Phys. Rev. B, $\textbf{80}$, 12 (2009)], our single-point approach allows to calculate the spin Chern number even when the spin operator $\hat{s}_z$ does not commute with the Hamiltonian, as in the presence of Rashba spin-orbit coupling. We validate our method on the Kane-Mele model, both pristine and in the presence of Anderson disorder. Finally, we investigate the disorder-driven transition from the trivial phase to the topological state known as topological Anderson insulator. Beyond disordered systems, our approach is particularly useful to investigate the role of defects, to study topological alloys and in the context of ab-initio molecular dynamics simulations at finite temperature.
48. SAFER: Situation Aware Facial Emotion Recognition
Authors: Mijanur Palash, Bharat Bhargava
Categories: cs.CV
Published: 2023-06-14
arXiv: 2306.09372v1
Abstract:
In this paper, we present SAFER, a novel system for emotion recognition from facial expressions. It employs state-of-the-art deep learning techniques to extract various features from facial images and incorporates contextual information, such as background and location type, to enhance its performance. The system has been designed to operate in an open-world setting, meaning it can adapt to unseen and varied facial expressions, making it suitable for real-world applications. An extensive evaluation of SAFER against existing works in the field demonstrates improved performance, achieving an accuracy of 91.4% on the CAER-S dataset. Additionally, the study investigates the effect of novelty such as face masks during the Covid-19 pandemic on facial emotion recognition and critically examines the limitations of mainstream facial expressions datasets. To address these limitations, a novel dataset for facial emotion recognition is proposed. The proposed dataset and the system are expected to be useful for various applications such as human-computer interaction, security, and surveillance.
49. Semi-supervised music emotion recognition using noisy student training and harmonic pitch class profiles
Authors: Hao Hao Tan
Categories: cs.SD, cs.LG, eess.AS
Published: 2021-12-01
arXiv: 2112.00702v2
Abstract:
We present Mirable’s submission to the 2021 Emotions and Themes in Music challenge. In this work, we intend to address the question: can we leverage semi-supervised learning techniques on music emotion recognition? With that, we experiment with noisy student training, which has improved model performance in the image classification domain. As the noisy student method requires a strong teacher model, we further delve into the factors including (i) input training length and (ii) complementary music representations to further boost the performance of the teacher model. For (i), we find that models trained with short input length perform better in PR-AUC, whereas those trained with long input length perform better in ROC-AUC. For (ii), we find that using harmonic pitch class profiles (HPCP) consistently improve tagging performance, which suggests that harmonic representation is useful for music emotion tagging. Finally, we find that noisy student method only improves tagging results for the case of long training length. Additionally, we find that ensembling representations trained with different training lengths can improve tagging results significantly, which suggest a possible direction to explore incorporating multiple temporal resolutions in the network architecture for future work.
50. Natural Language Processing for Cognitive Analysis of Emotions
Authors: Gustave Cortal, Alain Finkel, Patrick Paroubek, Lina Ye
Categories: cs.CL
Published: 2022-10-11
arXiv: 2210.05296v1
Abstract:
Emotion analysis in texts suffers from two major limitations: annotated gold-standard corpora are mostly small and homogeneous, and emotion identification is often simplified as a sentence-level classification problem. To address these issues, we introduce a new annotation scheme for exploring emotions and their causes, along with a new French dataset composed of autobiographical accounts of an emotional scene. The texts were collected by applying the Cognitive Analysis of Emotions developed by A. Finkel to help people improve on their emotion management. The method requires the manual analysis of an emotional event by a coach trained in Cognitive Analysis. We present a rule-based approach to automatically annotate emotions and their semantic roles (e.g. emotion causes) to facilitate the identification of relevant aspects by the coach. We investigate future directions for emotion analysis using graph structures.