Global Thread-Level Inference for Comment Classification in Community Question Answering

TL;DR

This paper proposes a global thread-level inference method for comment classification in community question answering, leveraging relations between comments to improve answer quality prediction, validated on a benchmark dataset.

Contribution

It introduces a novel approach that exploits comment relations at the thread level using graph-cut and ILP frameworks, enhancing classification accuracy.

Findings

Results outperform previous state-of-the-art methods.

Thread-level information significantly improves classification.

Validated on SemEval-2015 dataset.

Abstract

Community question answering, a recent evolution of question answering in the Web context, allows a user to quickly consult the opinion of a number of people on a particular topic, thus taking advantage of the wisdom of the crowd. Here we try to help the user by deciding automatically which answers are good and which are bad for a given question. In particular, we focus on exploiting the output structure at the thread level in order to make more consistent global decisions. More specifically, we exploit the relations between pairs of comments at any distance in the thread, which we incorporate in a graph-cut and in an ILP frameworks. We evaluated our approach on the benchmark dataset of SemEval-2015 Task 3. Results improved over the state of the art, confirming the importance of using thread level information.