Feature extraction and  classification of movie reviews

Nhamo Mtetwa; Awukam Ojang Awukam; Mehdi Yousefi

doi:10.1109/ISCMI.2018.8703235

Feature extraction and classification of movie reviews

Nhamo Mtetwa, Awukam Ojang Awukam, Mehdi Yousefi

Cyber Security and Networks

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

992 Downloads (Pure)

Abstract

Sentiment analysis identifies a user’s attitude towards a service, a topic or an event and it is very useful for companies that receive many written reviews of their services.We investigate the effect of feature extraction techniques on supervised machine learning classifiers using four different performance metrics using a publicly available movie review dataset. Our objective is to explore different classification algorithms as well as utilizing diverse feature extractors and compare outcomes and finally select the trio of feature extraction technique, classification algorithm and performance metric with the best result for the movie review classification use case.

Original language	English
Title of host publication	2018 5th International Conference on Soft Computing & Machine Intelligence (ISCMI)
Publisher	IEEE
Pages	67-71
Number of pages	5
ISBN (Electronic)	9781728113012
DOIs	https://doi.org/10.1109/ISCMI.2018.8703235
Publication status	Published - 2 May 2019

Publication series

Name
ISSN (Electronic)	2640-0146

Keywords

feature extraction
machine learning
sentiment analysis
Support Vector Machine (SVM)
random forest

Documents and Links

10.1109/ISCMI.2018.8703235

Mtetwa, N. et al (2019) Feature extraction and classification of movie reviews
Copyright © 2019 IEEE. This is a post-peer review, pre-copy edited version of the article and may differ slightly from the final published version of the work. This work is made available in line with the publisher policy. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
Author accepted manuscript, 672 KB

Cite this

@inproceedings{54ead7ebb8794d20bef7ac2a18260deb,

title = "Feature extraction and classification of movie reviews",

abstract = "Sentiment analysis identifies a user{\textquoteright}s attitude towards a service, a topic or an event and it is very useful for companies that receive many written reviews of their services.We investigate the effect of feature extraction techniques on supervised machine learning classifiers using four different performance metrics using a publicly available movie review dataset. Our objective is to explore different classification algorithms as well as utilizing diverse feature extractors and compare outcomes and finally select the trio of feature extraction technique, classification algorithm and performance metric with the best result for the movie review classification use case.",

keywords = "feature extraction, machine learning, sentiment analysis, Support Vector Machine (SVM), random forest",

author = "Nhamo Mtetwa and Awukam, {Awukam Ojang} and Mehdi Yousefi",

note = "Acceptance in SAN Changed to conf. proceedings from paper Exception email to author. ET 14/11/19 ",

year = "2019",

month = may,

day = "2",

doi = "10.1109/ISCMI.2018.8703235",

language = "English",

publisher = "IEEE",

pages = "67--71",

booktitle = "2018 5th International Conference on Soft Computing & Machine Intelligence (ISCMI)",

}

TY - GEN

T1 - Feature extraction and classification of movie reviews

AU - Mtetwa, Nhamo

AU - Awukam, Awukam Ojang

AU - Yousefi, Mehdi

N1 - Acceptance in SAN Changed to conf. proceedings from paper Exception email to author. ET 14/11/19

PY - 2019/5/2

Y1 - 2019/5/2

N2 - Sentiment analysis identifies a user’s attitude towards a service, a topic or an event and it is very useful for companies that receive many written reviews of their services.We investigate the effect of feature extraction techniques on supervised machine learning classifiers using four different performance metrics using a publicly available movie review dataset. Our objective is to explore different classification algorithms as well as utilizing diverse feature extractors and compare outcomes and finally select the trio of feature extraction technique, classification algorithm and performance metric with the best result for the movie review classification use case.

AB - Sentiment analysis identifies a user’s attitude towards a service, a topic or an event and it is very useful for companies that receive many written reviews of their services.We investigate the effect of feature extraction techniques on supervised machine learning classifiers using four different performance metrics using a publicly available movie review dataset. Our objective is to explore different classification algorithms as well as utilizing diverse feature extractors and compare outcomes and finally select the trio of feature extraction technique, classification algorithm and performance metric with the best result for the movie review classification use case.

KW - feature extraction

KW - machine learning

KW - sentiment analysis

KW - Support Vector Machine (SVM)

KW - random forest

U2 - 10.1109/ISCMI.2018.8703235

DO - 10.1109/ISCMI.2018.8703235

M3 - Conference contribution

SP - 67

EP - 71

BT - 2018 5th International Conference on Soft Computing & Machine Intelligence (ISCMI)

PB - IEEE

ER -