A Semi-supervised Approach for Profiling Online Reviewers

碩士 === 國立臺灣大學 === 資訊管理學研究所 === 105 === In the modern age where everyone can easily access a variety of information, online review has become an important source and will deeply affect one’s decision. The ability of knowing reviewers’ profiles is helpful for both customers and online retailers in man...

Full description

Bibliographic Details
Main Authors: Shih-Yu Shu, 書世祐
Other Authors: Chih-Ping Wei
Format: Others
Language:en_US
Published: 2017
Online Access:http://ndltd.ncl.edu.tw/handle/ev542b
id ndltd-TW-105NTU05396014
record_format oai_dc
spelling ndltd-TW-105NTU053960142019-05-15T23:39:36Z http://ndltd.ncl.edu.tw/handle/ev542b A Semi-supervised Approach for Profiling Online Reviewers 以半監督式方法來萃取線上評論者的用戶資訊 Shih-Yu Shu 書世祐 碩士 國立臺灣大學 資訊管理學研究所 105 In the modern age where everyone can easily access a variety of information, online review has become an important source and will deeply affect one’s decision. The ability of knowing reviewers’ profiles is helpful for both customers and online retailers in many ways. However, most of online review websites do not provide personal information of reviewers for the privacy concern, and the only clue that can be found is content of review. There is a research field called ‘user profiling’ which focuses on extracting user-profile attributes from corpus by using labeled datasets to train classifiers. Nevertheless, it is hard to get gold-standard datasets because of the lack of ground truth. As a result, many researchers found experts to help them label datasets, yet the manual annotation was a time-consuming and laborious task. In this paper, we propose a semi-supervised approach, trying to get labeled datasets without manual annotation. We conduct experiments to demonstrate the performance of our approach, comparing it with the ideal performance, and describe our observation. We hope that, one day, our method can be applied in user profiling, helping researchers save time on collecting gold-standard datasets, and focus on features extraction and classifier building. Chih-Ping Wei 魏志平 2017 學位論文 ; thesis 42 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 碩士 === 國立臺灣大學 === 資訊管理學研究所 === 105 === In the modern age where everyone can easily access a variety of information, online review has become an important source and will deeply affect one’s decision. The ability of knowing reviewers’ profiles is helpful for both customers and online retailers in many ways. However, most of online review websites do not provide personal information of reviewers for the privacy concern, and the only clue that can be found is content of review. There is a research field called ‘user profiling’ which focuses on extracting user-profile attributes from corpus by using labeled datasets to train classifiers. Nevertheless, it is hard to get gold-standard datasets because of the lack of ground truth. As a result, many researchers found experts to help them label datasets, yet the manual annotation was a time-consuming and laborious task. In this paper, we propose a semi-supervised approach, trying to get labeled datasets without manual annotation. We conduct experiments to demonstrate the performance of our approach, comparing it with the ideal performance, and describe our observation. We hope that, one day, our method can be applied in user profiling, helping researchers save time on collecting gold-standard datasets, and focus on features extraction and classifier building.
author2 Chih-Ping Wei
author_facet Chih-Ping Wei
Shih-Yu Shu
書世祐
author Shih-Yu Shu
書世祐
spellingShingle Shih-Yu Shu
書世祐
A Semi-supervised Approach for Profiling Online Reviewers
author_sort Shih-Yu Shu
title A Semi-supervised Approach for Profiling Online Reviewers
title_short A Semi-supervised Approach for Profiling Online Reviewers
title_full A Semi-supervised Approach for Profiling Online Reviewers
title_fullStr A Semi-supervised Approach for Profiling Online Reviewers
title_full_unstemmed A Semi-supervised Approach for Profiling Online Reviewers
title_sort semi-supervised approach for profiling online reviewers
publishDate 2017
url http://ndltd.ncl.edu.tw/handle/ev542b
work_keys_str_mv AT shihyushu asemisupervisedapproachforprofilingonlinereviewers
AT shūshìyòu asemisupervisedapproachforprofilingonlinereviewers
AT shihyushu yǐbànjiāndūshìfāngfǎláicuìqǔxiànshàngpínglùnzhědeyònghùzīxùn
AT shūshìyòu yǐbànjiāndūshìfāngfǎláicuìqǔxiànshàngpínglùnzhědeyònghùzīxùn
AT shihyushu semisupervisedapproachforprofilingonlinereviewers
AT shūshìyòu semisupervisedapproachforprofilingonlinereviewers
_version_ 1719151206280986624