紀要論文

感情分析を用いた口コミの正当性判定手法に関する研究

A STUDY ON METHODOLOGY FOR JUDGING THE LEGITIMACY OF WORD-OF-MOUTH USING SENTIMENT ANALYSIS

jpn

24368083

https://doi.org/10.15002/00030746

法政大学大学院理工学研究科

法政大学大学院紀要. 理工学研究科編

65

1

6

2024-03-24

Version of Record

In recent years, many people are influenced by posts on social networking services (SNS) when considering the purchase of products and other items, and the influence of word of mouth is growing. Because of this trend, SNS marketing is becoming more important for companies, and there is a growing need to analyze useful information from word-of-mouth that can be utilized for product development and other purposes. However, word-of-mouth includes malicious data such as slanderous remarks, and such data must be classified and excluded. Therefore, sentiment analysis, which can determine whether the content of word-of-mouth is positive or negative, is considered to be effective. In this study, we propose a method that uses sentiment analysis and machine learning to exclude malicious content from word-of-mouth and extract complaints that lead to points for improvement. We demonstrate the effectiveness of the proposed method by using about 12,000 postings for evaluation and analyzing them with well-defined features.

Article