Presentation 2018-12-07
Review analysis using machine learning interpretation method
Takayuki Onogawa, Yuichi Sei, Yasuyuki Tahara, Akihiko Ohsuga,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Many researches targeting review of goods and services are doing today. Although research is conducted from various viewpoints, there are few studies assuming situations such as "to compare concrete competitive products" that consumers often encounter. On the other hand, in recent years, research has been conducted to interpret the output of the machine learning model, so that human beings can understand the reasons for the output. LIME and SP-LIME are representative examples. Therefore, in this research, we analyze the machine learning model that classifies reviews on products by LIME and SP-LIME, and try to extract features of comparison of products seen by users.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Machine leaning / interpretability / natural language processing / LIME
Paper # AI2018-28
Date of Issue 2018-11-30 (AI)

Conference Information
Committee AI
Conference Date 2018/12/7(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Tsunenori Mine(Kyushu Univ.)
Vice Chair Daisuke Katagami(Tokyo Polytechnic Univ.) / Naoki Fukuta(Shizuoka Univ.)
Secretary Daisuke Katagami(Ritsumeikan Univ.) / Naoki Fukuta(Univ. of Electro-Comm.)
Assistant Yuko Sakurai(AIST)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Review analysis using machine learning interpretation method
Sub Title (in English)
Keyword(1) Machine leaning
Keyword(2) interpretability
Keyword(3) natural language processing
Keyword(4) LIME
1st Author's Name Takayuki Onogawa
1st Author's Affiliation The University of Electro-Communications(UEC)
2nd Author's Name Yuichi Sei
2nd Author's Affiliation The University of Electro-Communications(UEC)
3rd Author's Name Yasuyuki Tahara
3rd Author's Affiliation The University of Electro-Communications(UEC)
4th Author's Name Akihiko Ohsuga
4th Author's Affiliation The University of Electro-Communications(UEC)
Date 2018-12-07
Paper # AI2018-28
Volume (vol) vol.118
Number (no) AI-350
Page pp.pp.15-18(AI),
#Pages 4
Date of Issue 2018-11-30 (AI)