You talk what you read: Understanding News Comment Behavior by Dispositional and Situational Attribution

TL;DR

This paper investigates news comment behavior by modeling both user dispositional traits from interaction history and situational factors from news content, using a novel encoder-decoder framework to enhance understanding and applications like summarization.

Contribution

It introduces a three-part encoder-decoder model that captures dispositional and situational influences on news comments, advancing user behavior analysis in news comment mining.

Findings

Improved news summarization with reader-aware features

Enhanced news aspect-opinion forecasting accuracy

Validated model effectiveness in real-world applications

Abstract

Many news comment mining studies are based on the assumption that comment is explicitly linked to the corresponding news. In this paper, we observed that users' comments are also heavily influenced by their individual characteristics embodied by the interaction history. Therefore, we position to understand news comment behavior by considering both the dispositional factors from news interaction history, and the situational factors from corresponding news. A three-part encoder-decoder framework is proposed to model the generative process of news comment. The resultant dispositional and situational attribution contributes to understanding user focus and opinions, which are validated in applications of reader-aware news summarization and news aspect-opinion forecasting.