The University of Southampton
University of Southampton Institutional Repository

Domain identification for commercial intention-holding posts on Twitter

Domain identification for commercial intention-holding posts on Twitter
Domain identification for commercial intention-holding posts on Twitter
Today, more people use social networking platforms to convey their desires and recent needs. Actually, there are numerous daily posts carrying commercial intention. The detection of these kinds of user intention would be quite valuable, especially for the platform itself. Firstly, it could help the platform provide precise and instant recommendations to users for its own business interests. Secondly, intention mining works may help link users’ needs by detecting potential buyers and sellers and their specific intentions which can benefit users by optimizing the resources in their hand and increase functional richness.
The whole intention mining process generally includes three main stages: user commercial intention filtering, intention domain identification and specific intention words extraction. In this work, the first stage was simplified using
keywords-based automatic filter followed by a manual screening. The main focus of this paper is the second stage, assigning the intention-holding posts into their own single domain. Three machine learning models and two deep
learning models were proposed to solve this text classification problem. The proposed methods have been evaluated on a dataset containing 5500 real-time intention-holding tweets collected from Twitter. In general, the experimental
results showed impressive performance with the highest classification accuracy of 96% achieved by Long short-term memory.
IEEE
Zhu, Yuanyuan
f7a3fc17-f212-4087-9da8-414c0be26cdb
So, Mee
c6922ccf-547b-485e-8b74-a9271e6225a2
Harrigan, Paul
5b2e06f8-2065-4ed4-a5c6-f0e5601fbc4a
Zhu, Yuanyuan
f7a3fc17-f212-4087-9da8-414c0be26cdb
So, Mee
c6922ccf-547b-485e-8b74-a9271e6225a2
Harrigan, Paul
5b2e06f8-2065-4ed4-a5c6-f0e5601fbc4a

Zhu, Yuanyuan, So, Mee and Harrigan, Paul (2019) Domain identification for commercial intention-holding posts on Twitter. In International Conference on Cyber Situational Awareness, Data Analytics And Assessment. IEEE..

Record type: Conference or Workshop Item (Paper)

Abstract

Today, more people use social networking platforms to convey their desires and recent needs. Actually, there are numerous daily posts carrying commercial intention. The detection of these kinds of user intention would be quite valuable, especially for the platform itself. Firstly, it could help the platform provide precise and instant recommendations to users for its own business interests. Secondly, intention mining works may help link users’ needs by detecting potential buyers and sellers and their specific intentions which can benefit users by optimizing the resources in their hand and increase functional richness.
The whole intention mining process generally includes three main stages: user commercial intention filtering, intention domain identification and specific intention words extraction. In this work, the first stage was simplified using
keywords-based automatic filter followed by a manual screening. The main focus of this paper is the second stage, assigning the intention-holding posts into their own single domain. Three machine learning models and two deep
learning models were proposed to solve this text classification problem. The proposed methods have been evaluated on a dataset containing 5500 real-time intention-holding tweets collected from Twitter. In general, the experimental
results showed impressive performance with the highest classification accuracy of 96% achieved by Long short-term memory.

Full text not available from this repository.

More information

Published date: 3 June 2019
Venue - Dates: International Conference on Cyber Situational Awareness, Data Analytics And Assessment, Oxford, United Kingdom, 2019-06-03 - 2019-06-04

Identifiers

Local EPrints ID: 431483
URI: https://eprints.soton.ac.uk/id/eprint/431483
PURE UUID: ac5a9049-55f5-4aa6-b438-073bd8ee9421
ORCID for Mee So: ORCID iD orcid.org/0000-0002-8507-4222

Catalogue record

Date deposited: 05 Jun 2019 16:30
Last modified: 06 Jun 2019 00:33

Export record

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of https://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×