Semantic textual relatedness is crucial to Natural Language Processing (NLP). Methodologies often exhibit superior performance in high-resource languages such as English compared to low-resource ones like Marathi, Telugu, and Spanish. This study leverages various machine learning (ML) approaches, including Support Vector Regression (SVR) and Random Forest, deep learning (DL) techniques such as Siamese Neural Networks, and transformer-based models such as MiniLM-L6-v2, Marathi-sbert, Telugu-sentence-bert-nli, and Roberta-bne-sentiment-analysis-es, to assess semantic relatedness across English, Marathi, Telugu, and Spanish. The developed transformer-based methods notably outperformed other models in determining semantic textual relatedness across these languages, achieving a Spearman correlation coefficient of 0.822 (for English), 0.870 (for Marathi), 0.820 (for Telugu), and 0.677 (for Spanish). These results led to our work attaining rankings of 22th (for English), 11th (for Marathi), 11th (for Telegu) and 14th (for Spanish), respectively.

Intention detection is a crucial aspect of natural language understanding (NLU), focusing on identifying the primary objective underlying user input. In this work, we present a transformer-based method that excels in determining the intent of Arabic text within the banking domain. We explored several machine learning (ML), deep learning (DL), and transformer-based models on an Arabic banking dataset for intent detection. Our findings underscore the challenges that traditional ML and DL models face in understanding the nuances of various Arabic dialects, leading to subpar performance in intent detection. However, the transformer-based methods, designed to tackle such complexities, significantly outperformed the other models in classifying intent across different Arabic dialects. Notably, the AraBERTv2 model achieved the highest micro F1 score of 82.08% in ArBanking77 dataset, a testament to its effectiveness in this context. This achievement, which contributed to our work being ranked 5^th in the shared task, AraFinNLP2024, highlights the importance of developing models that can effectively handle the intricacies of Arabic language processing and intent detection.

Detecting propagandistic spans and identifying persuasion techniques are crucial for promoting informed decision-making, safeguarding democratic processes, and fostering a media environment characterized by integrity and transparency. Various machine learning (Logistic Regression, Random Forest, and Multinomial Naive Bayes), deep learning (CNN, CNN+LSTM, CNN+BiLSTM), and transformer-based (AraBERTv2, AraBERT-NER, CamelBERT, BERT-Base-Arabic) models were exploited to perform the task. The evaluation results indicate that CamelBERT achieved the highest micro-F1 score (24.09%), outperforming CNN+LSTM and AraBERTv2. The study found that most models struggle to detect propagandistic spans when multiple spans are present within the same article. Overall, the model’s performance secured a 6^th place ranking in the ArAIEval Shared Task-1.

The widespread use of online communication has caused a significant increase in the spread of hate speech on social media. However, there are also hate crimes based on caste and migration status. Despite several nations efforts to bring equality among their citizens, numerous crimes occur just based on caste. Migration-based hostility happens both in India and in developed countries. A shared task was arranged to address this issue in a low-resourced language such as Tamil. This paper aims to improve the detection of hate speech and hostility based on caste and migration status on social media. To achieve this, this work investigated several Machine Learning (ML), Deep Learning (DL), and transformer-based models, including M-BERT, XLM-R, and Tamil BERT. Experimental results revealed the highest macro f1-score of 0.80 using the M-BERT model, which enabled us to rank 3rd on the shared task.

The pervasive impact of stress on individuals necessitates proactive identification and intervention measures, especially in social media interaction. This research paper addresses the imperative need for proactive identification and intervention concerning the widespread influence of stress on individuals. This study focuses on the shared task, “Stress Identification in Dravidian Languages,” specifically emphasizing Tamil and Telugu code-mixed languages. The primary objective of the task is to classify social media messages into two categories: stressed and non stressed. We employed various methodologies, from traditional machine-learning techniques to state-of-the-art transformer-based models. Notably, the Tamil-BERT and Telugu-BERT models exhibited exceptional performance, achieving a noteworthy macro F1-score of 0.71 and 0.72, respectively, and securing the 15^th position in Tamil code-mixed language and the 9^th position in the Telugu code-mixed language. These findings underscore the effectiveness of these models in recognizing stress signals within social media content composed in Tamil and Telugu.

Hate and offensive language in online platforms pose significant challenges, necessitating automatic detection methods. Particularly in the case of codemixed text, which is very common in social media, the complexity of this problem increases due to the cultural nuances of different languages. DravidianLangTech-EACL2024 organized a shared task on detecting hate and offensive language for Telugu. To complete this task, this study investigates the effectiveness of transliteration-augmented datasets for Telugu code-mixed text. In this work, we compare the performance of various machine learning (ML), deep learning (DL), and transformer-based models on both original and augmented datasets. Experimental findings demonstrate the superiority of transformer models, particularly Telugu-BERT, achieving the highest f₁-score of 0.77 on the augmented dataset, ranking the 1^st position in the leaderboard. The study highlights the potential of transliteration-augmented datasets in improving model performance and suggests further exploration of diverse transliteration options to address real-world scenarios.

Due to technological advancements, various methods have emerged for disseminating news to the masses. The pervasive reach of news, however, has given rise to a significant concern: the proliferation of fake news. In response to this challenge, a shared task in Dravidian- LangTech EACL2024 was initiated to detect fake news and classify its types in the Malayalam language. The shared task consisted of two sub-tasks. Task 1 focused on a binary classification problem, determining whether a piece of news is fake or not. Whereas task 2 delved into a multi-class classification problem, categorizing news into five distinct levels. Our approach involved the exploration of various machine learning (RF, SVM, XGBoost, Ensemble), deep learning (BiLSTM, CNN), and transformer-based models (MuRIL, Indic- SBERT, m-BERT, XLM-R, Distil-BERT) by emphasizing parameter tuning to enhance overall model performance. As a result, we introduce a fine-tuned MuRIL model that leverages parameter tuning, achieving notable success with an F1-score of 0.86 in task 1 and 0.5191 in task 2. This successful implementation led to our system securing the 3rd position in task 1 and the 1st position in task 2. The source code will be found in the GitHub repository at this link: https://github.com/Salman1804102/ DravidianLangTech-EACL-2024-FakeNews.

The alarming rise of fake news on social media poses a significant threat to public discourse and decision-making. While automatic detection of fake news offers a promising solution, research in low-resource languages like Malayalam often falls behind due to limited data and tools. This paper presents the participation of team Punny_Punctuators in the Fake News Detection in Dravidian Languages shared task at DravidianLangTech@EACL 2024, addressing this gap. The shared task focuses on two sub-tasks: 1. classifying social media texts as original or fake, and 2. categorizing fake news into 5 categories. We experimented with various machine learning (ML), deep learning (DL) and transformer-based models as well as processing techniques such as transliteration. Malayalam-BERT achieved the best performance on both sub-tasks, which obtained us 2^nd place with a macro f₁-score of 0.87 for the subtask-1 and 11^th place with a macro f₁-score of 0.17 for the subtask-2. Our results highlight the potential of transformer models for low-resource languages in fake news detection and pave the way for further research in this crucial area.

In this modern era, many people have been using Facebook and Twitter, leading to increased information sharing and communication. However, a considerable amount of information on these platforms is misleading or intentionally crafted to deceive users, which is often termed as fake news. A shared task on fake news detection in Malayalam organized by DravidianLangTech@EACL 2024 allowed us for addressing the challenge of distinguishing between original and fake news content in the Malayalam language. Our approach involves creating an intelligent framework to categorize text as either fake or original. We experimented with various machine learning models, including Logistic Regression, Decision Tree, Random Forest, Multinomial Naive Bayes, SVM, and SGD, and various deep learning models, including CNN, BiLSTM, and BiLSTM + Attention. We also explored Indic-BERT, MuRIL, XLM-R, and m-BERT for transformer-based approaches. Notably, our most successful model, m-BERT, achieved a macro F1 score of 0.85 and ranked 4th in the shared task. This research contributes to combating misinformation on social media news, offering an effective solution to classify content accurately.

With the continuous evolution of technology and widespread internet access, various social media platforms have gained immense popularity, attracting a vast number of active users globally. However, this surge in online activity has also led to a concerning trend by driving many individuals to resort to posting hateful and offensive comments or posts, publicly targeting groups or individuals. In response to these challenges, we participated in this shared task. Our approach involved proposing a fine-tuning-based pre-trained transformer model to effectively discern whether a given text contains offensive content that propagates hatred. We conducted comprehensive experiments, exploring various machine learning (LR, SVM, and Ensemble), deep learning (CNN, BiLSTM, CNN+BiLSTM), and transformer-based models (Indic-SBERT, m- BERT, MuRIL, Distil-BERT, XLM-R), adhering to a meticulous fine-tuning methodology. Among the models evaluated, our fine-tuned L3Cube-Indic-Sentence-Similarity- BERT or Indic-SBERT model demonstrated superior performance, achieving a macro-average F1-score of 0.7013. This notable result positioned us at the 6th place in the task. The implementation details of the task will be found in the GitHub repository.

Textual Sentiment Analysis (TSA) delves into people’s opinions, intuitions, and emotions regarding any entity. Natural Language Processing (NLP) serves as a technique to extract subjective knowledge, determining whether an idea or comment leans positive, negative, neutral, or a mix thereof toward an entity. In recent years, it has garnered substantial attention from NLP researchers due to the vast availability of online comments and opinions. Despite extensive studies in this domain, sentiment analysis in low-resourced languages such as Tamil and Tulu needs help 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 explored four machine learning (ML) approaches (LR, SVM, XGBoost, Ensemble), four deep learning (DL) methods (BiLSTM and CNN with FastText and Word2Vec), and four transformer-based models (m-BERT, MuRIL, L3Cube-IndicSBERT, and Distilm-BERT) for both languages. For Tamil, L3Cube-IndicSBERT and ensemble approaches outperformed others, while m-BERT demonstrated superior performance among the models for Tulu. The presented models achieved the 3^rd and 1^st ranks by attaining macro F1-scores of 0.227 and 0.584 in Tamil and Tulu, respectively.

Detecting abusive language on social media is a challenging task that needs to be solved effectively. This research addresses the formidable challenge of detecting abusive language in Tamil through a comprehensive multimodal approach, incorporating textual, acoustic, and visual inputs. This study utilized ConvLSTM, 3D-CNN, and a hybrid 3D-CNN with BiLSTM to extract video features. Several models, such as BiLSTM, LR, and CNN, are explored for processing audio data, whereas for textual content, MNB, LR, and LSTM methods are explored. To further enhance overall performance, this work introduced a weighted late fusion model amalgamating predictions from all modalities. The fusion model was then applied to make predictions on the test dataset. The ConvLSTM+BiLSTM+MNB model yielded the highest macro F1 score of 71.43%. Our methodology allowed us to achieve 1 st rank for multimodal abusive language detection in the shared task

Identifying between fake and original news in social media demands vigilant procedures. This paper introduces the significant shared task on ‘Fake News Detection in Dravidian Languages - DravidianLangTech@EACL 2024’. With a focus on the Malayalam language, this task is crucial in identifying social media posts as either fake or original news. The participating teams contribute immensely to this task through their varied strategies, employing methods ranging from conventional machine-learning techniques to advanced transformer-based models. Notably, the findings of this work highlight the effectiveness of the Malayalam-BERT model, demonstrating an impressive macro F1 score of 0.88 in distinguishing between fake and original news in Malayalam social media content, achieving a commendable rank of 1st among the participants.

Sentiment analysis (SA) on social media reviews has become a challenging research agenda in recent years due to the exponential growth of textual content. Although several effective solutions are available for SA in high-resourced languages, it is considered a critical problem for low-resourced languages. This work introduces an automatic system for analyzing sentiment in Tamil and Tulu code-mixed languages. Several ML (DT, RF, MNB), DL (CNN, BiLSTM, CNN+BiLSTM), and transformer-based models (Indic-BERT, XLM-RoBERTa, m-BERT) are investigated for SA tasks using Tamil and Tulu code-mixed textual data. Experimental outcomes reveal that the transformer-based models XLM-R and m-BERT surpassed others in performance for Tamil and Tulu, respectively. The proposed XLM-R and m-BERT models attained macro F1-scores of 0.258 (Tamil) and 0.468 (Tulu) on test datasets, securing the 2^nd and 5^th positions, respectively, in the shared task.

Fake news misleads people and may lead to real-world miscommunication and injury. 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 was 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 (LR, DT, RF, MNB), deep learning models (CNN, BiLSTM, CNN+BiLSTM), and transformer-based models (Indic-BERT, XLMR, Malayalam-BERT, m-BERT) for both subtasks. The experimental results demonstrate that transformer-based models, specifically m- BERT and Malayalam-BERT, outperformed others. The m-BERT model achieved superior performance in subtask 1 with macro F1-scores of 0.84, and Malayalam-BERT outperformed the other models in subtask 2 with macro F1- scores of 0.496, securing us the 5th and 2nd positions in subtask 1 and subtask 2, respectively.

The amount of online textual content has increased significantly in recent years through social media posts, online chatting, web portals, and other digital platforms due to the significant increase in internet users and their unprompted access via digital devices. Unfortunately, the misappropriation of textual communication via the Internet has led to violence-inciting texts. Despite the availability of various forms of violence-inciting materials, text-based content is often used to carry out violent acts. Thus, developing a system to detect violence-inciting text has become vital. However, creating such a system in a low-resourced language like Bangla becomes challenging. Therefore, a shared task has been arranged to detect violence-inciting text in Bangla. This paper presents a hybrid approach (GAN+Bangla-ELECTRA) to classify violence-inciting text in Bangla into three classes: direct, passive, and non-violence. We investigated a variety of deep learning (CNN, BiLSTM, BiLSTM+Attention), machine learning (LR, DT, MNB, SVM, RF, SGD), transformers (BERT, ELECTRA), and GAN-based models to detect violence inciting text in Bangla. Evaluation results demonstrate that the GAN+Bangla-ELECTRA model gained the highest macro f₁-score (74.59), which obtained us a rank of 3rd position at the BLP-2023 Task 1.