Malta

Sentiment analysis delves into people&#39;s opinions, intuitions, and emotions regarding any entity. Within natural language processing (NLP), it serves as a technique to extract subjective knowledge, determining whether an opinion or comment leans positive, negative, neutral, or a mix thereof towards an entity. In recent years, it has garnered substantial attention from NLP researchers due to the vast availability of comments and opinions on the internet. Despite extensive studies in this domain, sentiment analysis in low-resource languages such as Tamil and Tulu faces challenges in handling code-mixed and transliterated content. To address these challenges, this work focuses on sentiment analysis of code-mixed and transliterated Tamil and Tulu social media comments. It explores four machine learning approaches (LR, SVM, XGBoost, Ensemble), two deep learning methods (BiLSTM with fastText and Word2Vec), and four transformer-based models (m-BERT, MuRIL, L3Cube-IndicSBERT, and DistilmBERT) for both languages. For Tamil, L3Cube-IndicSBERT and ensemble approaches outperform others, while m-BERT demonstrates superior performance among the models for Tulu. The presented models achieved the third and first ranks by attaining macro F1-scores of 0.227 and 0.584 in Tamil and Tulu, respectively.

EACL 2024

CUET_Binary_Hackers@DravidianLangTech-EACL 2024: Sentiment Analysis using Transformer-Based Models in Code-Mixed and Transliterated Tamil and Tulu

fasttext and word2vec

l3cube-indicsbert

muril

Welcome to the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL). Continuing its mission of expanding and involving the science community of all European countries, EACL has selected the Malta community for the 18th EACL. Considering the importance of physical interaction among researchers, the conference will be held at the Hotel Radisson Blu, St. Julians, in Malta, from 17 to 22 of March, 2024. The conference will also feature the possibility to participate virtually. As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language. 
#### [Conference Handbook](https://drive.google.com/file/d/13Wn38q0yev6U3RTgnf4Tn5T9GuAuZ-xW/view?usp=sharing) *downloadable*

To access the EACL 2024 event page you need to register [**here**](https://acl.swoogo.com/EACL2024). 

Please register!

As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

Sentiment analysis delves into people's opinions, intuitions, and emotions regarding any entity. Within natural language processing (NLP), it serves as a technique to extract subjective knowledge, determining whether an opinion or comment leans positive, negative, neutral, or a mix thereof towards an entity. In recent years, it has garnered substantial attention from NLP researchers due to the vast availability of comments and opinions on the internet. Despite extensive studies in this domain, sentiment analysis in low-resource languages such as Tamil and Tulu faces challenges in handling code-mixed and transliterated content. To address these challenges, this work focuses on sentiment analysis of code-mixed and transliterated Tamil and Tulu social media comments. It explores four machine learning approaches (LR, SVM, XGBoost, Ensemble), two deep learning methods (BiLSTM with fastText and Word2Vec), and four transformer-based models (m-BERT, MuRIL, L3Cube-IndicSBERT, and DistilmBERT) for both languages. For Tamil, L3Cube-IndicSBERT and ensemble approaches outperform others, while m-BERT demonstrates superior performance among the models for Tulu. The presented models achieved the third and first ranks by attaining macro F1-scores of 0.227 and 0.584 in Tamil and Tulu, respectively.

workshop paper

Abusive language is a major problem on social media, which highlights the need for efficient detection methods to be developed. This research addresses the formidable challenge of detecting abusive language in Tamil through a comprehensive multimodal approach, incorporating textual, acoustic, and visual inputs. In the domain of video data, our study utilizes ConvLSTM, 3DCNN, and a hybrid 3DCNN with BiLSTM. For audio data, models such as LSTM, BiLSTM, RNN, LR, GNB, and RF are explored. Regarding textual content, we investigate MNB, LR, RF, RNN, LSTM, and BiLSTM. To further enhance overall performance, we introduce a weighted late fusion model amalgamating predictions from all modalities. The fusion model is then applied to make predictions on our test dataset, yielding macro f1 score of 71.43%. Within the shared task "Multimodal Abusive Language Detection and Sentiment Analysis in Dravidian Languages: DravidianLangTech@EACL 2024," this methodology has achieved the highest ranking for detecting abusive language detection in the Tamil.

Binary_Beasts@DravidianLangTech@EACL 2024: Multimodal Abusive Language Detection in Tamil: An Integrated Approach using ML and DL Techniques

Sentiment Analysis of Dravidian Languages has begun to garner attention recently as there is more need to analyze emotional responses and subjective opinions present in social media text. As this data is code-mixed and there are not many solutions to code-mixed text out there, we present to you a stellar solution to DravidianLangTech@EACL 2024: Sentiment Analysis in Tamil and Tulu task. To understand the sentiment of social media text, we used pre trained transformer models and feature extraction vectorizers to classify the data with results that placed us 11th in the rankings for the Tamil task and 8th for the Tulu task with a macro F1 score of 0.074 and 0.251 which shows the efficiency of our approach.

WordWizardsDravidianLangTech@EACL 2024: Sentiment Analysis in Tamil and Tulu

The importance of being able to identify between fake and original news in the arena of social media demands surveillance procedures. This paper simply establishes the shared task on 'Fake News Detection in Dravidian Languages - DravidianLangTech@EACL 2024.' Focused on the Malayalam language, the task entails identifying social media posts as either fake or original news. The participating teams presented varied strategies, ranging from conventional machine-learning techniques to cutting-edge transformer-based models. Notably, our findings underscore the usefulness of the Malayalam-BERT model, demonstrating a noteworthy accuracy of 88% in detecting between fake and original news among Malayalam social media material.

CUET_DUO@DravidianLangTech 2024: Fake News Classification Using Malayalam-BERT

The main objective of the task is categorised into three subtasks. Subtask-1 Build models to determine the sentiment expressed in multimodal posts (or videos) in Tamil and Malayalam languages, leveraging textual, audio, and visual components. The videos are labelled into five categories: highly positive, positive, neutral, negative and highly negative. Subtask-2 Design machine models that effectively identify and classify abusive language within the multimodal context of social media posts in Tamil. The data are categorized into abusive and non-abusive categories. Subtask-3 Develop advanced models that accurately detect and categorize hate speech and offensive language in multimodal social media posts in Dravidian languages. The data points are categorized into Caste, Offensive, Racist and Sexist classes. In this session, the focus is primarily on Tamil language text data analysis. Various combination of machine learning models have been used to perform each tasks and do oversampling techniques to train models on biased dataset.

Wit Hub@DravidianLangTech-2024:Multimodal Social Media Data Analysis in Dravidian Languages using machine learning models

Social media reviews are utilized in sentiment analysis (SA), a computing area that analyses people's thoughts, and attitudes which has increased the need for efficient tools to analyze and determine feelings in such content. To tackle this challenge, our study introduces a system developed for the shared task of analyzing sentiment in Tamil and Tulu code-mixed languages. We utilized a combination of ML models (DT, RF, MNB, SVM), DL models (CNN, BiLSTM, CNN+BiLSTM with FastText), and transformer-based models (Indic-BERT, XLM-RoBERTa, m-BERT) for both Tamil and Tulu code-mixed language. Experimental outcomes reveal that the transformer-based models XLM-RoBERTa and m-BERT surpassed others in performance for Tamil and Tulu, respectively. The proposed XLM-RoBERTa and m-BERT models attained macro F1-scores of 0.258 and 0.468 for the Tamil and Tulu datasets, securing the 2nd and 5th positions, respectively, in the shared task competition.

CUETSentimentSillies@DravidianLangTech-EACL2024: Transformer-based approach for Sentiment Analysis in Tamil and Tulu Code-Mixed Text

Even though the improper use of social me- dia is increasing nowadays, there is also tech- nology that brings solutions. Here, improper- ness is posting hate and offensive speech that might harm an individual or group. Hate speech refers to an insult toward an individual or group based on their identities. Spreading it on so- cial media platforms is a serious problem for society. The solution, on the other hand, is the availability of natural language process- ing(NLP) technology that is capable to detect and handle such problems. This paper presents the detection of social media’s hate and offen- sive speech in the code-mixed Telugu language. For this, the task and golden standard dataset were provided for us by the shared task orga- nizer(DravidianLangTech@EACL 2024). To this end, we have employed the TF-IDF tech- nique for numeric feature extraction and used a random forest algorithm for modeling hate speech detection. Finally, the developed model was evaluated on the test dataset and achieved 0.492 macro-F1.

Social Media Hate and Offensive Speech Detection Using Machine Learning method

False news misleads people and may lead to real-world miscommunication and injury. Identifying fake news teaches society. Removing misinformation encourages critical thinking, democracy, and the prevention of hatred, fear, and misunderstanding. Identifying and removing fake news and developing a detection system is essential for reliable, accurate, and clear information. Therefore a shared task is organized to detect fake news in Malayalam. This paper presents a system developed for the shared task of detecting and classifying fake news in Malayalam. The approach involves a combination of machine learning models(DT, RF, MNB, SVM), deep learning models (CNN, BiLSTM, CNN+BiLSTM with FastText), and transformer-based models (Indic-BERT, indic-BERT, m-BERT) for both subtasks. The experimental results demonstrate that transformer-based models, specifically m-BERT and Malayalam-BERT, outperformed others. They achieved superior performance with noteworthy macro F1-scores of 0.84 and 0.496 for subtask 1 and subtask 2, respectively, securing the 5th and 2nd positions in the shared task competition.

CUETSentimentSillies@DravidianLangTech-EACL2024: Transformer-based approach for Detecting and Categorizing Fake News in Malayalam Language

TThe rise of social media has facilitated easier communication, information sharing, and current affairs updates. However, the prevalence of misleading and deceptive content, commonly referred to as fake news, poses a significant challenge. This paper focuses on the classification of fake news in Malayalam, a Dravidian language, utilizing natural language processing (NLP) techniques. To develop a model, we employed a random forest machine learning method on a dataset provided by a shared task(DravidianLangTech@EACL 2024). When evaluated by the separate test dataset, our developed model achieved a 0.71 macro F1 measure.

Social Media Fake News Classification Using Machine Learning Algorithm

The use of deep learning algorithms has resulted in significant progress in automatic speech recognition (ASR). Robust high-accuracy ASR models typically require thousands or tens of thousands of hours of speech data, but even the strongest models tend fail under noisy conditions. Unsurprisingly, the impact of noise on accuracy is more drastic in low-resource settings. In this paper, we investigate the impact of noise on ASR in a low-resource setting. We explore novel methods for developing noise-robust ASR models using a a small dataset for Tamil, a widely-spoken but under-resourced Dravidian languages. We add various noises to the audio data to determine the impact of different kinds of noise (e.g., punctuated vs. constant, man-made vs natural) We also explore the relationship between different data augmentation methods are better suited to handling different types of noise. Our results show that all noises, regardless of the type, had an impact on ASR performance, and that upgrading the architecture alone could not mitigate the impact of noise. SpecAugment, the most common data augmentation method, was not as helpful as raw data augmentation, in which noise is explicitly added to the training data. Raw data augmentation enhances ASR performance on both clean data and noise-mixed data.

Exploring the impact of noise in low-resource ASR for Tam

Hate and offensive language detection is the task of detecting hate and/or offensive content targetting a person or a group of people. Despite many efforts to detect hate and offensive content on social media platforms, the problem remains unsolved till date due to the ever growing social media users and their creativity to create and spread hate and offensive content. To address the automatic detection of hate and offensive content on social media platforms, this paper describes the learning models submitted by our team - MUCS to "Hate and Offensive Language Detection in Telugu Codemixed Text (HOLD-Telugu): DravidianLangTech@EACL" - a shared task organized at European Chapter of the Association for Computational Linguistics (EACL) 2024 invites the research community to address the challenges of detecting hate and offensive language in Telugu language. In this paper, we - team MUCS, describe the learning models submitted to the above mentioned shared task. Three models: Three models: i) LR model - a Machine Learning (ML) algorithm fed with TF-IDF of n-grams of subword, word and char_wb are in the range (1, 3), (1, 3), and (1, 5), ii) TL- a pretrained BERT models which makes use of Hate-speech-CNERG/bert-base-uncased-hatexplain model and iii) Ensemble model which is the combination of ML classifieres( MNB, LR, GNB) trained CountVectorizer with word and char ngrams of range (1, 3) and (1, 5) respectively. Proposed LR model trained with TF-IDF of subword, word and char n-grams outperformed the other models with macro F1 scores of 0.6501 securing 15th rank in the shared task for Telugu text.

Downloads

Next from EACL 2024

Binary_Beasts@DravidianLangTech@EACL 2024: Multimodal Abusive Language Detection in Tamil: An Integrated Approach using ML and DL Techniques

Similar lecture

CUETSentimentSillies@DravidianLangTech-EACL2024: Transformer-based approach for Sentiment Analysis in Tamil and Tulu Code-Mixed Text