English-Malay Cross-Lingual Emotion Detection In Tweets Using Word Embedding Alignment
The three-phase methodology to address the goals of this study included the construction of the English-Malay cross-lingual word embedding using word embedding alignment, enrichment of the cross-lingual word embedding with sentiment information, and pre-training of the hierarchical attention model s...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | http://eprints.usm.my/60433/ http://eprints.usm.my/60433/1/Pages%20from%20LIM%20YING%20HAO%20-%20TESIS.pdf |
| _version_ | 1848884444355624960 |
|---|---|
| author | Lim, Ying Hao |
| author_facet | Lim, Ying Hao |
| author_sort | Lim, Ying Hao |
| building | USM Institutional Repository |
| collection | Online Access |
| description | The three-phase methodology to address the goals of this study included the construction of the English-Malay cross-lingual word embedding using word embedding alignment, enrichment of the cross-lingual word embedding with sentiment information, and pre-training of the hierarchical attention model solely on English tweets. We evaluated our model in two scenarios: zero-shot learning and few-shot learning on 4176 Malay tweets annotated with emotion. We also examined the optimal number of Malay tweets required to finetune the model and the effect of finetuning different layers in our model. |
| first_indexed | 2025-11-15T19:06:48Z |
| format | Thesis |
| id | usm-60433 |
| institution | Universiti Sains Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T19:06:48Z |
| publishDate | 2023 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | usm-604332024-04-26T08:01:52Z http://eprints.usm.my/60433/ English-Malay Cross-Lingual Emotion Detection In Tweets Using Word Embedding Alignment Lim, Ying Hao QA75.5-76.95 Electronic computers. Computer science The three-phase methodology to address the goals of this study included the construction of the English-Malay cross-lingual word embedding using word embedding alignment, enrichment of the cross-lingual word embedding with sentiment information, and pre-training of the hierarchical attention model solely on English tweets. We evaluated our model in two scenarios: zero-shot learning and few-shot learning on 4176 Malay tweets annotated with emotion. We also examined the optimal number of Malay tweets required to finetune the model and the effect of finetuning different layers in our model. 2023-03 Thesis NonPeerReviewed application/pdf en http://eprints.usm.my/60433/1/Pages%20from%20LIM%20YING%20HAO%20-%20TESIS.pdf Lim, Ying Hao (2023) English-Malay Cross-Lingual Emotion Detection In Tweets Using Word Embedding Alignment. Masters thesis, Universiti Sains Malaysia. |
| spellingShingle | QA75.5-76.95 Electronic computers. Computer science Lim, Ying Hao English-Malay Cross-Lingual Emotion Detection In Tweets Using Word Embedding Alignment |
| title | English-Malay Cross-Lingual Emotion Detection In Tweets Using Word Embedding Alignment |
| title_full | English-Malay Cross-Lingual Emotion Detection In Tweets Using Word Embedding Alignment |
| title_fullStr | English-Malay Cross-Lingual Emotion Detection In Tweets Using Word Embedding Alignment |
| title_full_unstemmed | English-Malay Cross-Lingual Emotion Detection In Tweets Using Word Embedding Alignment |
| title_short | English-Malay Cross-Lingual Emotion Detection In Tweets Using Word Embedding Alignment |
| title_sort | english-malay cross-lingual emotion detection in tweets using word embedding alignment |
| topic | QA75.5-76.95 Electronic computers. Computer science |
| url | http://eprints.usm.my/60433/ http://eprints.usm.my/60433/1/Pages%20from%20LIM%20YING%20HAO%20-%20TESIS.pdf |