| dc.contributor.author |
Sharma, Yashvardhan |
|
| dc.date.accessioned |
2024-11-15T07:04:35Z |
|
| dc.date.available |
2024-11-15T07:04:35Z |
|
| dc.date.issued |
2020 |
|
| dc.identifier.uri |
https://www.academia.edu/download/88147088/T4-4.pdf |
|
| dc.identifier.uri |
http://dspace.bits-pilani.ac.in:8080/jspui/handle/123456789/16389 |
|
| dc.description.abstract |
This paper presents the methodologies implemented while classifying Dravidian code-mixed comments
according to their polarity in the evaluation of the track ‘Sentiment Analysis for Davidian Languages in
Code-Mixed Text’ proposed by Forum of Information Retrieval Evaluation in 2020. The implemented
method used a sub-word level representation to capture the sentiment of the text. Using a Long Short
Term Memory (LSTM) network along with language-specific preprocessing, the model classified the text
according to its polarity. With F1-scores of 0.61 and 0.60, the model achieved an overall rank of 5 and 12
in the Tamil and Malayalam tasks respectively. |
en_US |
| dc.language.iso |
en |
en_US |
| dc.publisher |
CEUR-WS |
en_US |
| dc.subject |
Computer Science |
en_US |
| dc.subject |
Sentiment analysis |
en_US |
| dc.subject |
Recurrent neural networks |
en_US |
| dc.subject |
Sub-word Analysis |
en_US |
| dc.title |
Bits2020@ Dravidian-CodeMix-FIRE2020: Sub-Word Level Sentiment Analysis of Dravidian Code Mixed Data |
en_US |
| dc.type |
Article |
en_US |