ECO v1: Towards Event-Centric Opinion Mining

TL;DR

This paper introduces the task of event-centric opinion mining, proposing a new framework, constructing a pioneering dataset, and demonstrating its feasibility and challenges for future research.

Contribution

It formulates the novel task of event-centric opinion mining, creates the first benchmark dataset, and provides baseline methods for future exploration.

Findings

Event-centric opinion mining is feasible but challenging.

The constructed dataset supports future research.

Baseline methods show promising results.

Abstract

Events are considered as the fundamental building blocks of the world. Mining event-centric opinions can benefit decision making, people communication, and social good. Unfortunately, there is little literature addressing event-centric opinion mining, although which significantly diverges from the well-studied entity-centric opinion mining in connotation, structure, and expression. In this paper, we propose and formulate the task of event-centric opinion mining based on event-argument structure and expression categorizing theory. We also benchmark this task by constructing a pioneer corpus and designing a two-step benchmark framework. Experiment results show that event-centric opinion mining is feasible and challenging, and the proposed task, dataset, and baselines are beneficial for future studies.