让印尼语情感分析模型理解话题背景，提升判断准确性。
IndoBERT-Sentiment: Context-Conditioned Sentiment Classification for Indonesian Text
- 输入话题上下文和文本，联合判断情感
- 在188个话题上达到F1宏值0.856，准确率88.1%
- 对传统方法误判的句子显著改善，适合多话题场景
现有印尼语情感分析模型孤立处理文本，忽略常决定情感倾向的话题背景。我们提出IndoBERT-Sentiment，一种基于话题上下文的情感分类器，同时接收话题上下文与待分析文本，输出与话题相关的合理情感判断。该模型基于IndoBERT Large（335M参数），在包含31,360组上下文-文本对、覆盖188个话题的数据集上训练，取得F1宏值0.856与准确率88.1%。在与三种主流通用印尼语情感模型的同测试集对比中，其表现领先最佳基线达35.6个F1点。实验表明，此前仅用于相关性分类的话题条件化机制，可有效迁移至情感分析任务，使模型正确识别出传统无上下文方法系统误判的文本。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。