Sentiment Analysis Using Common-Sense and Context Information

Abstract

Sentiment analysis research has been increasing tremendously in recent times due to the wide range of business and social applications. Sentiment analysis from unstructured natural language text has recently received considerable attention from the research community. In this paper, we propose a novel sentiment analysis model based on common-sense knowledge extracted from ConceptNet based ontology and context information. ConceptNet based ontology is used to determine the domain specific concepts which in turn produced the domain specific important features. Further, the polarities of the extracted concepts are determined using the contextual polarity lexicon which we developed by considering the context information of a word. Finally, semantic orientations of domain specific features of the review document are aggregated based on the importance of a feature with respect to the domain. The importance of the feature is determined by the depth of the feature in the ontology. Experimental results show the effectiveness of the proposed methods.

A New Approach to Ontology-Based Semantic Modelling for Opinion Mining

“…Zhao and Li [18], Peñalver-Martínez et al [14] and Agarwal et al [1] utilised SKB approaches that are mainly based on the knowledge background of the domain. SKB approaches demonstrated improved performance for feature extraction when the knowledge of the domain of interest is utilised to extract features.…”

“…Machine Learning approaches (ML) rely on a large set of training data to learn the features from a set of reviews [2,11,19]. Semantic Knowledge-Based approaches (SKB) are based on extracting features from reviews by utilising an ontology that contains a conceptualised knowledge background of the domain [1,14,18]. Several attempts on using the SKB approach to extract features using domain knowledge are discussed in the literature, and these present promising results in comparison with aforementioned ARM and ML approaches [3].…”

Sentiment Analysis using Word-Graphs

“…An alternative approach is the use of features that are contextually related to the document (e.g. [1,2,4]) especially when sentiment analysis is applied on social media which are rich in metadata and other activities of social context (e.g. "mentions", "likes", etc).…”

A proposed method for predicting US presidential election by analyzing sentiment in social media

“…Sentiment analysis uses Natural Language Processing (NLP) to collect opinion and examine opinion or sentiment words [11]. Based on [12], there are 2 important tasks in sentiment analysis. First, identify the opinion targets (aspects, entity, and topics).…”