Unsupervised Fuzzy-Multi-Core Aspect Sentiment Analysis for Big Data of Online News Users' Persian Opinions

• Published in: Asian Journal of Research in Computer Science Vol. 16; no. 3; pp. 50 - 64
• Main Authors: Azarkasb, Seyed Omid, Amiri, Mostafa, Khasteh, Seyed Hossein
• Format: Journal Article
• Language: English
• Published: 03.07.2023
• Subjects: Computer Science
• ISSN: 2581-8260; 2581-8260
• DOI: 10.9734/ajrcos/2023/v16i3345

An online news article can cover various topics or contain different aspects of a subject, encouraging readers to express their opinions on specific topics or aspects. Sentiment analysis evaluates the overall sentiment of the audience towards the entire news article, whether it is positive, negative, or neutral. However, in aspect-based sentiment analysis, the focus is on determining which aspect of the news article the opinion is referring to. Extracting the relevant aspect in sentiment analysis involves identifying the part of the article that the reader has expressed an opinion about. This task can lead to a more precise analysis of audience reactions to future news and events. To accomplish this, the news text is segmented into constituent sentences and transformed into a vector space. Then, an unsupervised clustering method is applied to extract various aspects of the news. Fuzzy multi-core clustering is employed as the clustering technique, which has lower computational overhead and can handle uncertain, noisy, and outlier data easily. The implemented approach is based on the concept of feasibility and utilizes multi-core learning to detect clusters in complex data structures. This method remains robust against issues such as ineffective cores or unrelated features by automatically adjusting the core weights within an optimized framework. Furthermore, support vector machines are employed to establish the relationship between opinions and relevant aspects. The transition to the vector space, the mapping process, clustering operations, and aspect extraction are performed in the reducer.