Sentiment analysis: towards a tool for analysing real-time students feedback

Nabeela Altrabsheh; Mihaela Cocea; Sanaz Fallahkhair

doi:10.1109/ICTAI.2014.70

Sentiment analysis: towards a tool for analysing real-time students feedback

Nabeela Altrabsheh, Mihaela Cocea, Sanaz Fallahkhair

University of Brighton

Research output: Chapter in Book/Conference proceeding with ISSN or ISBN › Conference contribution with ISSN or ISBN › peer-review

Abstract

Students' real-time feedback has numerous advantages in education, however, analysing feedback while teaching is both stressful and time consuming. To address this problem, we propose to analyse feedback automatically using sentiment analysis. Sentiment analysis is domain dependent and although it has been applied to the educational domain before, it has not been previously used for real-time feedback. To find the best model for automatic analysis we look at four aspects: preprocessing, features, machine learning techniques and the use of the neutral class. We found that the highest result for the four aspects is Support Vector Machines (SVM) with the highest level of preprocessing, unigrams and no neutral class, which gave a 95 percent accuracy.

Original language	English
Title of host publication	IEEE 26th international conference on tools with artificial intelligence
Place of Publication	Limassol, Cyprus
Publisher	IEEE
Pages	419-423
Number of pages	5
DOIs	https://doi.org/10.1109/ICTAI.2014.70
Publication status	Published - 31 Dec 2014
Event	IEEE 26th international conference on tools with artificial intelligence - Limassol, Cyprus, 10-12 Nov. 2014 Duration: 31 Dec 2014 → …

Conference

Conference	IEEE 26th international conference on tools with artificial intelligence
Period	31/12/14 → …

Bibliographical note

© 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, 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 component of this work in other works.

Keywords

Sentiment Analysis
Educational Data Mining
Feature Selection
Real-time Feedback

Access to Document

10.1109/ICTAI.2014.70Licence: Unspecified

ICTAI2014.pdfAccepted author manuscript, 98.6 KBLicence: Unspecified

Sanaz Fallahkhair
- S.Fallahkhairbrighton.acuk
- School of Arch, Tech and Eng - Principal Lecturer
- Computing and Mathematical Sciences Research Excellence Group
Person: Academic

Cite this

@inproceedings{23a8085d32c94f008339df26c9e7e918,

title = "Sentiment analysis: towards a tool for analysing real-time students feedback",

abstract = "Students' real-time feedback has numerous advantages in education, however, analysing feedback while teaching is both stressful and time consuming. To address this problem, we propose to analyse feedback automatically using sentiment analysis. Sentiment analysis is domain dependent and although it has been applied to the educational domain before, it has not been previously used for real-time feedback. To find the best model for automatic analysis we look at four aspects: preprocessing, features, machine learning techniques and the use of the neutral class. We found that the highest result for the four aspects is Support Vector Machines (SVM) with the highest level of preprocessing, unigrams and no neutral class, which gave a 95 percent accuracy.",

keywords = "Sentiment Analysis, Educational Data Mining, Feature Selection, Real-time Feedback",

author = "Nabeela Altrabsheh and Mihaela Cocea and Sanaz Fallahkhair",

note = "{\textcopyright} 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, 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 component of this work in other works.; IEEE 26th international conference on tools with artificial intelligence ; Conference date: 31-12-2014",

year = "2014",

month = dec,

day = "31",

doi = "10.1109/ICTAI.2014.70",

language = "English",

pages = "419--423",

booktitle = "IEEE 26th international conference on tools with artificial intelligence",

publisher = "IEEE",

}

Sentiment analysis: towards a tool for analysing real-time students feedback. / Altrabsheh, Nabeela; Cocea, Mihaela; Fallahkhair, Sanaz.
IEEE 26th international conference on tools with artificial intelligence. Limassol, Cyprus: IEEE, 2014. p. 419-423.

Research output: Chapter in Book/Conference proceeding with ISSN or ISBN › Conference contribution with ISSN or ISBN › peer-review

TY - GEN

T1 - Sentiment analysis: towards a tool for analysing real-time students feedback

AU - Altrabsheh, Nabeela

AU - Cocea, Mihaela

AU - Fallahkhair, Sanaz

N1 - © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, 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 component of this work in other works.

PY - 2014/12/31

Y1 - 2014/12/31

N2 - Students' real-time feedback has numerous advantages in education, however, analysing feedback while teaching is both stressful and time consuming. To address this problem, we propose to analyse feedback automatically using sentiment analysis. Sentiment analysis is domain dependent and although it has been applied to the educational domain before, it has not been previously used for real-time feedback. To find the best model for automatic analysis we look at four aspects: preprocessing, features, machine learning techniques and the use of the neutral class. We found that the highest result for the four aspects is Support Vector Machines (SVM) with the highest level of preprocessing, unigrams and no neutral class, which gave a 95 percent accuracy.

AB - Students' real-time feedback has numerous advantages in education, however, analysing feedback while teaching is both stressful and time consuming. To address this problem, we propose to analyse feedback automatically using sentiment analysis. Sentiment analysis is domain dependent and although it has been applied to the educational domain before, it has not been previously used for real-time feedback. To find the best model for automatic analysis we look at four aspects: preprocessing, features, machine learning techniques and the use of the neutral class. We found that the highest result for the four aspects is Support Vector Machines (SVM) with the highest level of preprocessing, unigrams and no neutral class, which gave a 95 percent accuracy.

KW - Sentiment Analysis

KW - Educational Data Mining

KW - Feature Selection

KW - Real-time Feedback

U2 - 10.1109/ICTAI.2014.70

DO - 10.1109/ICTAI.2014.70

M3 - Conference contribution with ISSN or ISBN

SP - 419

EP - 423

BT - IEEE 26th international conference on tools with artificial intelligence

PB - IEEE

CY - Limassol, Cyprus

T2 - IEEE 26th international conference on tools with artificial intelligence

Y2 - 31 December 2014

ER -

Sentiment analysis: towards a tool for analysing real-time students feedback

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Profiles

Sanaz Fallahkhair

Cite this