Sapna Negi

Suggestion Mining from Opinionated Text.

Abstract Products and services are heavily discussed on social media, which are conventionally used by brand owners, as well as consumers, to acquire consumer opinions. State-of-the-art opinion mining systems provide summaries of positive and negative sentiments toward a service/product and its various aspects. On a closer look, it is observed that these opinions also contain suggestions, tips, and advice, which are often explicitly sought by both brand owners and consumers. This chapter presents a comprehensive overview of the task of mining suggestions from the opinionated text on social media. Various aspects of the task are discussed, which includes an analysis of suggestions appearing in reviews, the relation between sentiments and suggestions, relevant datasets, and existing methods. The problem has been identified only recently as a viable task, and there is limited availability of existing approaches and datasets.

A Study of Suggestions in Opinionated Texts and their Automatic Detection.

We study the automatic detection of suggestion expressing text among the opinionated text. The examples of such suggestions in online reviews would be, customer suggestions about improvement in a commercial entity, and advice to the fellow customers. We present a qualitative and quantitative analysis of suggestions present in the text samples obtained from social media platforms. Suggestion mining from social media is an emerging research area, and thus problem definition and datasets are still evolving; this work also contributes towards the same. The problem has been formulated as a sentence classification task, and we compare the results of some popular supervised learning approaches in this direction. We also evaluate different kinds of features with these classifiers. The experiments indicate that deep learning based approaches tend to be promising for this task.

INSIGHT Galway: Syntactic and Lexical Features for Aspect Based Sentiment Analysis

This work analyses various syntactic and lexical features for sentence level aspect based sentiment analysis. The task focuses on detection of a writer’s sentiment towards an aspect which is explicitly mentioned in a sentence. The target sentiment polarities are positive, negative, conflict and neutral. We use a supervised learning approach, evaluate various features and report accuracies which are much higher than the provided baselines. Best features include unigrams, clauses, dependency relations and SentiWordNet polarity scores.