GADFA: Generator-Assisted Decision-Focused Approach for Opinion Expressing Timing Identification

TL;DR

The paper addresses identifying when professionals should express opinions in response to news by formalizing the task of news-triggered opinion expressing timing and introducing the Generator-Assisted Decision-Focused Approach (GADFA). GADFA couples two generators (opinion and risk reminder) with a decision model that uses generated content and the original news to predict whether to release a report, trained on a large Chinese stock–news–report dataset collected from 2014–2020. The authors demonstrate that augmenting the decision model with generated opinions and risk reminders improves timing identification performance, with Mengzi T5 often yielding the strongest results, especially when using more recent news ($T=5$). This work advances AI-assisted professional decision-making in finance and offers a foundation for extending the approach to other domains, while acknowledging limitations such as language scope and the absence of human evaluation for the generated content.

Abstract

The advancement of text generation models has granted us the capability to produce coherent and convincing text on demand. Yet, in real-life circumstances, individuals do not continuously generate text or voice their opinions. For instance, consumers pen product reviews after weighing the merits and demerits of a product, and professional analysts issue reports following significant news releases. In essence, opinion expression is typically prompted by particular reasons or signals. Despite long-standing developments in opinion mining, the appropriate timing for expressing an opinion remains largely unexplored. To address this deficit, our study introduces an innovative task - the identification of news-triggered opinion expressing timing. We ground this task in the actions of professional stock analysts and develop a novel dataset for investigation. Our approach is decision-focused, leveraging text generation models to steer the classification model, thus enhancing overall performance. Our experimental findings demonstrate that the text generated by our model contributes fresh insights from various angles, effectively aiding in identifying the optimal timing for opinion expression.

Figures (2)

• Figure 1: Illustration of the proposed GADFA.
• Figure 2: Distribution of report release date within year. Dataset and All denote the statistics of the experimental dataset and all reports from 2014 to 2020, respectively.