Aspect-based sentiment analysis of Sindhi newspaper articles

• Main Authors: Sodhar, Irum Naz, Sulaiman, Suriani, Buller, Abdul Hafeez, Sodhar, Anam Naz
• Format: Article
• Language: English
• Published: International Journal of Computer Science and Network Security (IJCSNS) 2022
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://irep.iium.edu.my/98465/7/98465_Aspect-based%20sentiment%20analysis%20of%20Sindhi%20newspaper%20articles.pdf; http://irep.iium.edu.my/98465/; http://paper.ijcsns.org/07_book/202205/20220554.pdf
• Institution: Universiti Islam Antarabangsa Malaysia

Aspect-Based Sentiment Analysis (ABSA) is a type of sentiment analysis that categorizes the polarity of sentiment based on the most important attributes of an entity related to a product, service or target. This research work presented a statistical study of Aspect-Based Sentiment Analysis on the dataset collected from the official website of Sindhi newspaper. There are various official newspaper websites available on the internet for Sindhi but focused on one official website that is Awami Awaz. In this research work, the dataset contains five sentences and one hundred and fifty-two words with punctuations, numbers and symbols chosen from the newspaper website. The dataset was first performed pre-processing task which were tokenized and after that identified Aspect-Based Sentiment Analysis from text context. The results of the Aspect-Based Sentiment Analysis are analyzed based one three categories: confidence level, positive polarity, and negative polarity. The pre-processing tasks were performed using the Sindhi NLP tool which is freely available online by a single search on google search engine. This tool contains multiple features available for the research purpose related to Sindhi Text.