IndoBERT-Sentiment: Context-Conditioned Sentiment Classification for Indonesian Text
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913015995039744 |
|---|---|
| author | Saputra, Muhammad Apriandito Arya Alamsyah, Andry Ramadhani, Dian Puteri Siadari, Thomhert Suprapto Fakhrurroja, Hanif |
| author_facet | Saputra, Muhammad Apriandito Arya Alamsyah, Andry Ramadhani, Dian Puteri Siadari, Thomhert Suprapto Fakhrurroja, Hanif |
| contents | Existing Indonesian sentiment analysis models classify text in isolation, ignoring the topical context that often determines whether a statement is positive, negative, or neutral. We introduce IndoBERT-Sentiment, a context-conditioned sentiment classifier that takes both a topical context and a text as input, producing sentiment predictions grounded in the topic being discussed. Built on IndoBERT Large (335M parameters) and trained on 31,360 context-text pairs labeled across 188 topics, the model achieves an F1 macro of 0.856 and accuracy of 88.1%. In a head-to-head evaluation against three widely used general-purpose Indonesian sentiment models on the same test set, IndoBERT-Sentiment outperforms the best baseline by 35.6 F1 points. We show that context-conditioning, previously demonstrated for relevancy classification, transfers effectively to sentiment analysis and enables the model to correctly classify texts that are systematically misclassified by context-free approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_07057 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | IndoBERT-Sentiment: Context-Conditioned Sentiment Classification for Indonesian Text Saputra, Muhammad Apriandito Arya Alamsyah, Andry Ramadhani, Dian Puteri Siadari, Thomhert Suprapto Fakhrurroja, Hanif Computation and Language 68T50 I.2.7; H.3.3 Existing Indonesian sentiment analysis models classify text in isolation, ignoring the topical context that often determines whether a statement is positive, negative, or neutral. We introduce IndoBERT-Sentiment, a context-conditioned sentiment classifier that takes both a topical context and a text as input, producing sentiment predictions grounded in the topic being discussed. Built on IndoBERT Large (335M parameters) and trained on 31,360 context-text pairs labeled across 188 topics, the model achieves an F1 macro of 0.856 and accuracy of 88.1%. In a head-to-head evaluation against three widely used general-purpose Indonesian sentiment models on the same test set, IndoBERT-Sentiment outperforms the best baseline by 35.6 F1 points. We show that context-conditioning, previously demonstrated for relevancy classification, transfers effectively to sentiment analysis and enables the model to correctly classify texts that are systematically misclassified by context-free approaches. |
| title | IndoBERT-Sentiment: Context-Conditioned Sentiment Classification for Indonesian Text |
| topic | Computation and Language 68T50 I.2.7; H.3.3 |
| url | https://arxiv.org/abs/2604.07057 |