This paper provides a comprehensive summary of the “Homophobia and Transphobia Detection in Social Media Comments” shared task, which was held at the LT-EDI@EACL 2024. The objective of this task was to develop systems capable of identifying instances of homophobia and transphobia within social media comments. This challenge was extended across ten languages: English, Tamil, Malayalam, Telugu, Kannada, Gujarati, Hindi, Marathi, Spanish, and Tulu. Each comment in the dataset was annotated into three categories. The shared task attracted significant interest, with over 60 teams participating through the CodaLab platform. The submission of prediction from the participants was evaluated with the macro F1 score.

This working-notes are about the participation of the UMUTeam in a LT-EDI shared task concerning the identification of homophobic and transphobic comments in YouTube. These comments are written in English, which has high availability to machine-learning resources; Tamil, which has fewer resources; and a transliteration from Tamil to Roman script combined with English sentences. To carry out this shared task, we train a neural network that combines several feature sets applying a knowledge integration strategy. These features are linguistic features extracted from a tool developed by our research group and contextual and non-contextual sentence embeddings. We ranked 7th for English subtask (macro f1-score of 45%), 3rd for Tamil subtask (macro f1-score of 82%), and 2nd for Tamil-English subtask (macro f1-score of 58%).

Depression is a mental condition related to sadness and the lack of interest in common daily tasks. In this working-notes, we describe the proposal of the UMUTeam in the LT-EDI shared task (ACL 2022) concerning the identification of signs of depression in social network posts. This task is somehow related to other relevant Natural Language Processing tasks such as Emotion Analysis. In this shared task, the organisers challenged the participants to distinguish between moderate and severe signs of depression (or no signs of depression at all) in a set of social posts written in English. Our proposal is based on the combination of linguistic features and several sentence embeddings using a knowledge integration strategy. Our proposal achieved the 6th position, with a macro f1-score of 53.82 in the official leader board.

Hope Speech detection is the task of classifying a sentence as hope speech or non-hope speech given a corpus of sentences. Hope speech is any message or content that is positive, encouraging, reassuring, inclusive and supportive that inspires and engenders optimism in the minds of people. In contrast to identifying and censoring negative speech patterns, hope speech detection is focussed on recognising and promoting positive speech patterns online. In this paper, we report an overview of the findings and results from the shared task on hope speech detection for Tamil, Malayalam, Kannada, English and Spanish languages conducted in the second workshop on Language Technology for Equality, Diversity and Inclusion (LT-EDI-2022) organised as a part of ACL 2022. The participants were provided with annotated training & development datasets and unlabelled test datasets in all the five languages. The goal of the shared task is to classify the given sentences into one of the two hope speech classes. The performances of the systems submitted by the participants were evaluated in terms of micro-F1 score and weighted-F1 score. The datasets for this challenge are openly available

This working notes summarises the participation of the UMUTeam on the TamilNLP (ACL 2022) shared task concerning emotion analysis in Tamil. We participated in the two multi-classification challenges proposed with a neural network that combines linguistic features with different feature sets based on contextual and non-contextual sentence embeddings. Our proposal achieved the 1st result for the second subtask, with an f1-score of 15.1% discerning among 30 different emotions. However, our results for the first subtask were not recorded in the official leader board. Accordingly, we report our results for this subtask with the validation split, reaching a macro f1-score of 32.360%.

Social media has become a dangerous place as bullies take advantage of the anonymity the Internet provides to target and intimidate vulnerable individuals and groups. In the past few years, the research community has focused on developing automatic classification tools for detecting hate-speech, its variants, and other types of abusive behaviour. However, these methods are still at an early stage in low-resource languages. With the aim of reducing this barrier, the TamilNLP shared task has proposed a multi-classification challenge for Tamil written in Tamil script and code-mixed to detect abusive comments and hope-speech. Our participation consists of a knowledge integration strategy that combines sentence embeddings from BERT, RoBERTa, FastText and a subset of language-independent linguistic features. We achieved our best result in code-mixed, reaching 3rd position with a macro-average f1-score of 35%.

In this manuscript we describe the participation of the UMUTeam on the MAMI shared task proposed at SemEval 2022. This task is concerning the identification of misogynous content from a multi-modal perspective. Our participation is grounded on the combination of different feature sets within the same neural network. Specifically, we combine linguistic features with contextual transformers based on text (BERT) and images (BEiT). Besides, we also evaluate other ensemble learning strategies and the usage of non-contextual pretrained embeddings. Although our results are limited, we outperform all the baselines proposed, achieving position 36 in the binary classification task with a macro F1-score of 0.687, and position 28 in the multi-label task of misogynous categorisation, with an macro F1-score of 0.663.

In this manuscript we detail the participation of the UMUTeam in the iSarcasm shared task (SemEval-2022). This shared task is related to the identification of sarcasm in English and Arabic documents. Our team achieve in the first challenge, a binary classification task, a F1 score of the sarcastic class of 17.97 for English and 31.75 for Arabic. For the second challenge, a multi-label classification, our results are not recorded due to an unknown problem. Therefore, we report the results of each sarcastic mechanism with the validation split. For our proposal, several neural networks that combine language-independent linguistic features with pre-trained embeddings are trained. The embeddings are based on different schemes, such as word and sentence embeddings, and contextual and non-contextual embeddings. Besides, we evaluate different techniques for the integration of the feature sets, such as ensemble learning and knowledge integration. In general, our best results are achieved using the knowledge integration strategy.