Domain-Specific Aspect-Sentiment Pair Extraction Using Rules and Compound Noun Lexicon for Customer Reviews
Journal Title: Informatics - Year 2018, Vol 5, Issue 4
Abstract
Online reviews are an important source of opinion to measure products’ quality. Hence, automated opinion mining is used to extract important features (aspect) and related comments (sentiment). Extraction of correct aspect-sentiment pairs is critical for overall outcome of opinion mining; however, current works still have limitations in terms of identifying special compound noun and parent-child relationship aspects in the extraction process. To address these problems, an aspect-sentiment pair extraction using the rules and compound noun lexicon (ASPERC) model is proposed. The model consists of three main phases, such as compound noun lexicon generation, aspect-sentiment pair rule generation, and aspect-sentiment pair extraction. The combined approach of rules generated from training sentences and domain specific compound noun lexicon enable extraction of more aspects by firstly identifying special compound noun and parent-child aspects, which eventually contribute to more aspect-sentiment pair extraction. The experiment is conducted with the SemEval 2014 dataset to compare proposed and baseline models. Both ASPERC and its variant, ASPER, result higher in recall (28.58% and 22.55% each) compared to baseline and satisfactorily extract more aspect sentiment pairs. Lastly, the reasonable outcome of ASPER indicates applicability of rules to various domains.
Authors and Affiliations
Noor Rizvana Ahamed Kabeer, Keng Hoon Gan and Erum Haris
Keywords
Related Articles
- EP ID EP44155
- DOI https://doi.org/10.3390/informatics5040045
- Views 256
- Downloads 0
Mobile Phones Help Develop Listening Skills
Listening is one of the most difficult language skills among the four communication competences; however, it has received much less time in English learning than the other three (reading, writing, and speaking). Also,...
From Offshore Operation to Onshore Simulator: Using Visualized Ethnographic Outcomes to Work with Systems Developers
This paper focuses on the process of translating insights from a Computer Supported Cooperative Work (CSCW)-based study, conducted on a vessel at sea, into a model that can assist systems developers working with simulato...
Artificial Neural Networks and Particle Swarm Optimization Algorithms for Preference Prediction in Multi-Criteria Recommender Systems
Recommender systems are powerful online tools that help to overcome problems of information overload. They make personalized recommendations to online users using various data mining and filtering techniques. However,...
Theory and Practice in Digital Behaviour Change: A Matrix Framework for the Co-Production of Digital Services That Engage, Empower and Emancipate Marginalised People Living with Complex and Chronic Conditions
Background: The WHO framework on integrated people-centred health services promotes a focus on the needs of people and their communities to empower them to have a more active role in their own health. It has advocated...
Constructing Interactive Visual Classification, Clustering and Dimension Reduction Models for n-D Data
The exploration of multidimensional datasets of all possible sizes and dimensions is a long-standing challenge in knowledge discovery, machine learning, and visualization. While multiple efficient visualization methods...