Concepedia

Jointly Modeling Aspects and Opinions with a MaxEnt-LDA Hybrid

Xin Zhao, Jing Jiang, Hongfei Yan, Xiaoming Li

Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University) · 2010 · 414 citations · 15 references

Full text

Open access

TL;DR

Online review summarization aims to extract opinions, yet existing topic models fail to link aspect‑specific opinion words, making the task challenging. The study proposes a MaxEnt‑LDA hybrid model to jointly discover aspects and their specific opinion words. It integrates a maximum‑entropy framework with Latent Dirichlet Allocation to jointly learn aspect and opinion word distributions. With limited training data, the model accurately identifies aspect and opinion words and adapts across domains.

Abstract

Discovering and summarizing opinions from online reviews is an important and challenging task. A commonly-adopted framework generates structured review summaries with aspects and opinions. Recently topic models have been used to identify meaningful review aspects, but existing topic models do not identify aspect-specific opinion words. In this paper, we propose a MaxEnt-LDA hybrid model to jointly discover both aspects and aspect-specific opinion words. We show that with a relatively small amount of training data, our model can effectively identify aspect and opinion words simultaneously. We also demonstrate the domain adaptability of our model.