Aspect-Level Obfuscated Sentiment in Thai Financial Disclosures and Its Impact on Abnormal Returns
Attapol T. Rutherford, Sirisak Chueykamhang, Thachaparn Bunditlurdruk, Nanthicha Angsuwichitkul
TL;DR
The paper tackles obfuscated sentiment in Thai financial disclosures and its link to abnormal stock returns. It develops an Aspect-Based Sentiment Analysis framework with 16 aspects, builds a publicly available annotated dataset from Form 56-1, and benchmarks BERT-based models against lexical baselines. An event-study reveals that market reactions are driven by specific aspects and that negative sentiment in the MD&A section can be particularly informative, while overall polarity often misleads. By releasing the dataset and demonstrating effective ABSA with WangchanBERTa, the work provides a valuable resource and methodological advance for financial NLP in the Thai market.
Abstract
Understanding sentiment in financial documents is crucial for gaining insights into market behavior. These reports often contain obfuscated language designed to present a positive or neutral outlook, even when underlying conditions may be less favorable. This paper presents a novel approach using Aspect-Based Sentiment Analysis (ABSA) to decode obfuscated sentiment in Thai financial annual reports. We develop specific guidelines for annotating obfuscated sentiment in these texts and annotate more than one hundred financial reports. We then benchmark various text classification models on this annotated dataset, demonstrating strong performance in sentiment classification. Additionally, we conduct an event study to evaluate the real-world implications of our sentiment analysis on stock prices. Our results suggest that market reactions are selectively influenced by specific aspects within the reports. Our findings underscore the complexity of sentiment analysis in financial texts and highlight the importance of addressing obfuscated language to accurately assess market sentiment.