SentiHood: Targeted Aspect Based Sentiment Analysis Dataset for Urban Neighbourhoods

TL;DR

This paper introduces SentiHood, a new dataset for targeted aspect-based sentiment analysis in urban neighborhoods, addressing the challenge of extracting fine-grained opinions from social media QA platform texts.

Contribution

It presents the first dataset from a QA platform for fine-grained sentiment analysis and develops baseline models using logistic regression and neural networks.

Findings

SentiHood enables targeted sentiment analysis on social media data.

Baseline models achieve competitive performance on the dataset.

The dataset captures diverse opinions on urban neighborhoods.

Abstract

In this paper, we introduce the task of targeted aspect-based sentiment analysis. The goal is to extract fine-grained information with respect to entities mentioned in user comments. This work extends both aspect-based sentiment analysis that assumes a single entity per document and targeted sentiment analysis that assumes a single sentiment towards a target entity. In particular, we identify the sentiment towards each aspect of one or more entities. As a testbed for this task, we introduce the SentiHood dataset, extracted from a question answering (QA) platform where urban neighbourhoods are discussed by users. In this context units of text often mention several aspects of one or more neighbourhoods. This is the first time that a generic social media platform in this case a QA platform, is used for fine-grained opinion mining. Text coming from QA platforms is far less constrained compared to text from review specific platforms which current datasets are based on. We develop several strong baselines, relying on logistic regression and state-of-the-art recurrent neural networks.