Sentiment analysis enhancement with target variable in Kumar's Algorithm

International Conference on Innovation in Engineering and Vocational Education

自然科学;教育

Arman, A.A.^1 ; Kawi, A.B.^1 ; Hurriyati, R.^1

Sekolah Teknik Elektro Dan Informatika, Institut Teknologi Bandung, Jl. Ganesha 10, Bandung, Indonesia^1

关键词: Customer services;    Modified algorithms;    Public opinions;    Sentiment scores;    Social media;    Source material;    Subjective information;    Text analysis;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/128/1/012019/pdf
DOI  :  10.1088/1757-899X/128/1/012019

来源: IOP

【 摘 要 】

Sentiment analysis (also known as opinion mining) refers to the use of text analysis and computational linguistics to identify and extract subjective information in source materials. Sentiment analysis is widely applied to reviews discussion that is being talked in social media for many purposes, ranging from marketing, customer service, or public opinion of public policy. One of the popular algorithm for Sentiment Analysis implementation is Kumar algorithm that developed by Kumar and Sebastian. Kumar algorithm can identify the sentiment score of the statement, sentence or tweet, but cannot determine the relationship of the object or target related to the sentiment being analysed. This research proposed solution for that challenge by adding additional component that represent object or target to the existing algorithm (Kumar algorithm). The result of this research is a modified algorithm that can give sentiment score based on a given object or target.