Table 1 Compilation of projects employing XLM-RoBERTa Algorithm.
From: Sentiment classification for telugu using transformed based approaches on a multi-domain dataset
S. No | Paper Title | Language | Classification | Model | Performance Metrics |
|---|---|---|---|---|---|
1 | Ref- 39 | Tamil | Aspect based sentiment analysis | XLM-RoBERTa | Accuracy-46% |
2 | Ref- 38 | Bengali Language | Sentiment Classification | XLM-RoBERTa | Accuracy-95% |
3 | Ref- 45 | Kannada Malayalam Tamil | Offensive Language Identification | XLM-RoBERTa | F1 Score-69%, 92%,76% |
4 | Ref- 36 | Hindi-English Spanish-English | Sentiment Classification | XLM-RoBERTa | F1 score- 70% |
5 | Ref- 32 | English to Hindi | Sentiment Classification | XLM-RoBERTa | Accuracy-71.8% |
6 | Ref- 44 | Malayalam English and Tamil-English | Sentiment Polarity | XLM-RoBERTa | F1 score- 74% |
7 | Ref- 40 | 30 Languages | Sentiment Classification | XLM-RoBERTa | F1 score- 73.4% |
8 | Ref-42 | Tamil | Aspect Based Emotion Analysis | XLM-RoBERTa | F1 score- 32% |
9 | Ref- 46 | French | Sentiment Analysis | XLM-RoBERTa | Accuracy-74.4% |
10 | Ref- 34 | Tamil-English Malayalam-English Kannada-English | Sentiment classification | XLM-RoBERTa | F1 Score- 71.1% 75.3% 62.3% |
11 | Ref- 47 | English | Sentiment classification | XLM-RoBERTa | Accuracy- 73% |
12 | Ref- 35 | Spanish-English | Sentiment Classification | XLM-RoBERTa | F1 score- 52.20% |
13 | Ref- 43 | Roman Urdu and English text | Sentiment Classification | XLM-RoBERTa | F1 score- 71% |
14 | Ref- 41 | Kannada-English | Sentiment Classification | XLM-RoBERTa | F1 score- 80% |
15 | Ref- 48 | Kinyarwanda and English | Sentiment Classification | XLM-RoBERTa | F1 Score- 59% |
16 | Ref- 49 | Spanish | Emotion Classification | XLM-RoBERTa | F1 Score- 55% |
17 | Ref- 37 | Tamil-English and Malayalam-English | Sentiment Analysis | XLM-RoBERTa | F1 Score- 76% |
18 | Ref- 50 | English & Indonesian | Text Classification | XLM-RoBERTa | Accuracy- 90.02% |
