Sean Benhur (2022) TamilEmo: Finegrained Emotion Detection Dataset for Tamil. TamilEmo: Finegrained Emotion Detection Dataset for Tamil.

[thumbnail of TamilEmo Finegrained Emotion Detection Dataset for Tamil.pdf] Text
TamilEmo Finegrained Emotion Detection Dataset for Tamil.pdf - Accepted Version
Download (558kB)

Abstract

Emotional Analysis from textual input has been considered both a challenging and interesting task in Natural
Language Processing. However due to the lack of datasets in low-resource languages (i.e. Tamil), it is difficult to
conduct research of high standard in this area. Therefore we introduce this labeled dataset (a largest manually
annotated dataset of more than 42k Tamil YouTube comments, labeled for 31 emotions including neutral) for
emotion recognition. The goal of this dataset is to improve emotion detection in multiple downstream tasks in
Tamil.We have also created three different groupings of our emotions (3-class, 7-class and 31-class) and evaluated
the model’s performance on each category of the grouping. Our MURIL- base model has achieved a 0.60 macro
average F1-score across our 3-class group dataset. With 7-class and 31-class groups, the Random Forest model
performed well with a macro average F1-scores of 0.42 and 0.29 respectively

Item Type: Article
Uncontrolled Keywords: Emotion Detection, Tamil, Corpus, YouTube Comments, Textual Inpu
Depositing User: Mr Team Mosys
Date Deposited: 05 May 2025 08:51
Last Modified: 05 May 2025 08:51
URI: https://ir.psgcas.ac.in/id/eprint/2408

Actions (login required)

View Item
View Item