Presentation 2012-08-02
Information Recommender Based on User's Preference Extracted from Voice Data
Hiroshi Honda, Kousuke Takano,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we present a user preference profiling method from speech recognized information for personalized recommendation. Our method mainly consists of two phases: a process of term-weighting based on a user preference profile and a process of noise terms-filtering that are stored in the user preference profile as the result of wrong speech recognition. A user preference profile constructed by our method allows a user to obtain recommended items according to interest of the user. In this study, by means of several experiments using our prototype, we show the feasibility of our proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Information recommender / voice data / user profile / information browsing behavior / preference
Paper # DE2012-23
Date of Issue

Conference Information
Committee DE
Conference Date 2012/7/25(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Data Engineering (DE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Information Recommender Based on User's Preference Extracted from Voice Data
Sub Title (in English)
Keyword(1) Information recommender
Keyword(2) voice data
Keyword(3) user profile
Keyword(4) information browsing behavior
Keyword(5) preference
1st Author's Name Hiroshi Honda
1st Author's Affiliation Kanagawa Institute of Technology()
2nd Author's Name Kousuke Takano
2nd Author's Affiliation Kanagawa Institute of Technology
Date 2012-08-02
Paper # DE2012-23
Volume (vol) vol.112
Number (no) 172
Page pp.pp.-
#Pages 6
Date of Issue