Cover Image

Split Over-Training for Unsupervised Purchase Intention Identification

Recognizing user-expressed intentions in social media can be useful for many applications such as business intelligence, as intentions are intimately linked to potential actions or behaviors. This paper focuses on a binary classification problem: whether a text expresses purchase intention (PI) o...

Full description

Saved in:
Bibliographic Details
Main Authors: Abd Yusof, Noor Fazilla, Lin, Chenghua, Han, Xiwu, Barawi, Mohamad Hardyman
Format: E-Article
Language:English
Published: The World Academy of Research in Science and Engineering 2020
Subjects:
BF Psychology
QA75 Electronic computers. Computer science
Online Access:http://ir.unimas.my/id/eprint/30325/1/Split%20Over-Training%20for%20Unsupervised%20Purchase%20Intention%20Identification_abstract.pdf
http://ir.unimas.my/id/eprint/30325/
http://www.warse.org/
https://doi.org/10.30534/ijatcse/2020/214932020
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.unimas.ir.30325
record_format eprints
spelling my.unimas.ir.303252020-07-09T03:13:42Z http://ir.unimas.my/id/eprint/30325/ Split Over-Training for Unsupervised Purchase Intention Identification Abd Yusof, Noor Fazilla Lin, Chenghua Han, Xiwu Barawi, Mohamad Hardyman BF Psychology QA75 Electronic computers. Computer science Recognizing user-expressed intentions in social media can be useful for many applications such as business intelligence, as intentions are intimately linked to potential actions or behaviors. This paper focuses on a binary classification problem: whether a text expresses purchase intention (PI) or not (non- PI). In contrast to existing research, which relies on labeled intention corpus or linguistic knowledge, we proposed an unsupervised method called split over-training for the PI identification task. Experiments on PI identification from tweets showed that our approach was effective and promising. The best classifying accuracy of 84.6% and PI F-measure of 70.4% was achieved, which are only 7.7% and 4.9% respectively lower than fully supervised models. This means our unsupervised method may provide reasonable preprocessing for intention corpus labeling or intention knowledge acquisition. The World Academy of Research in Science and Engineering 2020-06 E-Article PeerReviewed text en http://ir.unimas.my/id/eprint/30325/1/Split%20Over-Training%20for%20Unsupervised%20Purchase%20Intention%20Identification_abstract.pdf Abd Yusof, Noor Fazilla and Lin, Chenghua and Han, Xiwu and Barawi, Mohamad Hardyman (2020) Split Over-Training for Unsupervised Purchase Intention Identification. International Journal of Advanced Trends in Computer Science and Engineering, 9 (3). pp. 3921-3928. ISSN 2278-3091 http://www.warse.org/ https://doi.org/10.30534/ijatcse/2020/214932020
institution Universiti Malaysia Sarawak
building Centre for Academic Information Services (CAIS)
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Sarawak
content_source UNIMAS Institutional Repository
url_provider http://ir.unimas.my/
language English
topic BF Psychology
QA75 Electronic computers. Computer science
spellingShingle BF Psychology
QA75 Electronic computers. Computer science
Abd Yusof, Noor Fazilla
Lin, Chenghua
Han, Xiwu
Barawi, Mohamad Hardyman
Split Over-Training for Unsupervised Purchase Intention Identification
description Recognizing user-expressed intentions in social media can be useful for many applications such as business intelligence, as intentions are intimately linked to potential actions or behaviors. This paper focuses on a binary classification problem: whether a text expresses purchase intention (PI) or not (non- PI). In contrast to existing research, which relies on labeled intention corpus or linguistic knowledge, we proposed an unsupervised method called split over-training for the PI identification task. Experiments on PI identification from tweets showed that our approach was effective and promising. The best classifying accuracy of 84.6% and PI F-measure of 70.4% was achieved, which are only 7.7% and 4.9% respectively lower than fully supervised models. This means our unsupervised method may provide reasonable preprocessing for intention corpus labeling or intention knowledge acquisition.
format E-Article
author Abd Yusof, Noor Fazilla
Lin, Chenghua
Han, Xiwu
Barawi, Mohamad Hardyman
author_facet Abd Yusof, Noor Fazilla
Lin, Chenghua
Han, Xiwu
Barawi, Mohamad Hardyman
author_sort Abd Yusof, Noor Fazilla
title Split Over-Training for Unsupervised Purchase Intention Identification
title_short Split Over-Training for Unsupervised Purchase Intention Identification
title_full Split Over-Training for Unsupervised Purchase Intention Identification
title_fullStr Split Over-Training for Unsupervised Purchase Intention Identification
title_full_unstemmed Split Over-Training for Unsupervised Purchase Intention Identification
title_sort split over-training for unsupervised purchase intention identification
publisher The World Academy of Research in Science and Engineering
publishDate 2020
url http://ir.unimas.my/id/eprint/30325/1/Split%20Over-Training%20for%20Unsupervised%20Purchase%20Intention%20Identification_abstract.pdf
http://ir.unimas.my/id/eprint/30325/
http://www.warse.org/
https://doi.org/10.30534/ijatcse/2020/214932020
_version_ 1672614443062657024
score 13.211869

Similar Items