User Personalized Satisfaction Prediction via Multiple Instance Deep Learning

TL;DR

This paper introduces a deep learning framework based on multiple instance learning to predict user satisfaction in community question answering, reducing manual feature engineering and improving personalized satisfaction prediction accuracy.

Contribution

It proposes a novel multiple instance deep learning approach for personalized satisfaction prediction, addressing limitations of manual feature selection in existing methods.

Findings

Effective in large-scale Stack Exchange datasets

Outperforms traditional feature-based methods

Extensible to other satisfaction prediction applications

Abstract

Community based question answering services have arisen as a popular knowledge sharing pattern for netizens. With abundant interactions among users, individuals are capable of obtaining satisfactory information. However, it is not effective for users to attain answers within minutes. Users have to check the progress over time until the satisfying answers submitted. We address this problem as a user personalized satisfaction prediction task. Existing methods usually exploit manual feature selection. It is not desirable as it requires careful design and is labor intensive. In this paper, we settle this issue by developing a new multiple instance deep learning framework. Specifically, in our settings, each question follows a weakly supervised learning multiple instance learning assumption, where its obtained answers can be regarded as instance sets and we define the question resolved with at least one satisfactory answer. We thus design an efficient framework exploiting multiple instance learning property with deep learning to model the question answer pairs. Extensive experiments on large scale datasets from Stack Exchange demonstrate the feasibility of our proposed framework in predicting askers personalized satisfaction. Our framework can be extended to numerous applications such as UI satisfaction Prediction, multi armed bandit problem, expert finding and so on.