Extracting Gamers' Opinions from Reviews

Maria-Dorinela Sirbu; Anna Secui; Mihai Dascalu; Scott Crossley; Stefan Ruseti; Stefan Trausan-Matu

doi:10.1109/SYNASC.2016.38

Extracting Gamers' Opinions from Reviews

Maria-Dorinela Sirbu, Anna Secui, Mihai Dascalu, Scott Crossley, Stefan Ruseti, Stefan Trausan-Matu

Research output: Chapter in Book/Report/Conference proceeding › Conference Article in proceeding › Academic

Abstract

Opinion mining and sentiment analysis are a trending research domain in Natural Language Processing focused on automatically extracting subjective information, feelings, opinions, ideas or emotions from texts. Our study is centered on identifying sentiments and opinions, as well as other latent linguistic dimensions expressed in on-line game reviews. Over 9500 entertainment game reviews from Amazon were examined using a Principal Component Analysis applied to word-count indices derived from linguistic resources. Eight affective components were identified as being the most representative semantic and sentiment-oriented dimensions for our dataset. These components explained 51.2% of the variance of all reviews. A Multivariate Analysis of Variance showed that five of the eight components demonstrated significant differences between positive, negative and neutral game reviews. These five components used as predictors in a Discriminant Function Analysis, were able to classify game reviews into positive, negative and neutral ratings with a 55% accuracy.

Original language	English
Title of host publication	SYNASC 2016
Subtitle of host publication	18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing
Editors	James Davenport, Viorel Negru, Tetsuo Ida, Tudor Jebelean, Stephen Watt, Daniela Zahaire
Publisher	IEEE
Pages	227-232
ISBN (Electronic)	978-1-5090-5707-8
DOIs	https://doi.org/10.1109/SYNASC.2016.38
Publication status	Published - Feb 2017
Externally published	Yes
Event	SYNASC 2016: 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing - Timisoara, Romania Duration: 24 Sept 2016 → 27 Sept 2016 https://synasc.ro/2016

Publication series

Series	SYNASC
ISSN	2470-881X

Conference

Conference	SYNASC 2016
Abbreviated title	SYNASC2016
Country/Territory	Romania
City	Timisoara
Period	24/09/16 → 27/09/16
Internet address	https://synasc.ro/2016

Keywords

Natural Language Processing
sentiment analysis
opinion mining
game reviews
lexical analysis

Access to Document

10.1109/SYNASC.2016.38Licence: CC BY-NC-SA

Rage: Realising an Applied Gaming Eco-system
Westera, W. (PI), Georgiadis, K. (CoI), Saveski, G. (CoI), van Lankveld, G. (CoI), Bahreini, K. (CoI), van der Vegt, W. (CoI), Berkhout, J. (CoI), Nyamsuren, E. (CoI), Kluijfhout, E. (CoI) & Nadolski, R. (CoI)
European Union
1/02/15 → 31/07/19
Project: Research

Cite this

Sirbu, M.-D., Secui, A., Dascalu, M., Crossley, S., Ruseti, S., & Trausan-Matu, S. (2017). Extracting Gamers' Opinions from Reviews. In J. Davenport, V. Negru, T. Ida, T. Jebelean, S. Watt, & D. Zahaire (Eds.), SYNASC 2016: 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (pp. 227-232). IEEE. https://doi.org/10.1109/SYNASC.2016.38

@inproceedings{2c483f2e893e48879a16fcd6169e0ee1,

title = "Extracting Gamers' Opinions from Reviews",

abstract = "Opinion mining and sentiment analysis are a trending research domain in Natural Language Processing focused on automatically extracting subjective information, feelings, opinions, ideas or emotions from texts. Our study is centered on identifying sentiments and opinions, as well as other latent linguistic dimensions expressed in on-line game reviews. Over 9500 entertainment game reviews from Amazon were examined using a Principal Component Analysis applied to word-count indices derived from linguistic resources. Eight affective components were identified as being the most representative semantic and sentiment-oriented dimensions for our dataset. These components explained 51.2% of the variance of all reviews. A Multivariate Analysis of Variance showed that five of the eight components demonstrated significant differences between positive, negative and neutral game reviews. These five components used as predictors in a Discriminant Function Analysis, were able to classify game reviews into positive, negative and neutral ratings with a 55% accuracy.",

keywords = "Natural Language Processing, sentiment analysis, opinion mining, game reviews, lexical analysis",

author = "Maria-Dorinela Sirbu and Anna Secui and Mihai Dascalu and Scott Crossley and Stefan Ruseti and Stefan Trausan-Matu",

year = "2017",

month = feb,

doi = "10.1109/SYNASC.2016.38",

language = "English",

series = "SYNASC",

publisher = "IEEE",

pages = " 227--232",

editor = "James Davenport and Viorel Negru and Tetsuo Ida and Tudor Jebelean and Stephen Watt and Daniela Zahaire",

booktitle = "SYNASC 2016",

address = "United States",

note = "SYNASC 2016 : 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC2016 ; Conference date: 24-09-2016 Through 27-09-2016",

url = "https://synasc.ro/2016",

}

Sirbu, M-D, Secui, A, Dascalu, M, Crossley, S, Ruseti, S & Trausan-Matu, S 2017, Extracting Gamers' Opinions from Reviews. in J Davenport, V Negru, T Ida, T Jebelean, S Watt & D Zahaire (eds), SYNASC 2016: 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing. IEEE, SYNASC, pp. 227-232, SYNASC 2016, Timisoara, Romania, 24/09/16. https://doi.org/10.1109/SYNASC.2016.38

Extracting Gamers' Opinions from Reviews. / Sirbu, Maria-Dorinela; Secui, Anna; Dascalu, Mihai et al.
SYNASC 2016: 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing. ed. / James Davenport; Viorel Negru; Tetsuo Ida; Tudor Jebelean; Stephen Watt; Daniela Zahaire. IEEE, 2017. p. 227-232 (SYNASC).

Research output: Chapter in Book/Report/Conference proceeding › Conference Article in proceeding › Academic

TY - GEN

T1 - Extracting Gamers' Opinions from Reviews

AU - Sirbu, Maria-Dorinela

AU - Secui, Anna

AU - Dascalu, Mihai

AU - Crossley, Scott

AU - Ruseti, Stefan

AU - Trausan-Matu, Stefan

PY - 2017/2

Y1 - 2017/2

N2 - Opinion mining and sentiment analysis are a trending research domain in Natural Language Processing focused on automatically extracting subjective information, feelings, opinions, ideas or emotions from texts. Our study is centered on identifying sentiments and opinions, as well as other latent linguistic dimensions expressed in on-line game reviews. Over 9500 entertainment game reviews from Amazon were examined using a Principal Component Analysis applied to word-count indices derived from linguistic resources. Eight affective components were identified as being the most representative semantic and sentiment-oriented dimensions for our dataset. These components explained 51.2% of the variance of all reviews. A Multivariate Analysis of Variance showed that five of the eight components demonstrated significant differences between positive, negative and neutral game reviews. These five components used as predictors in a Discriminant Function Analysis, were able to classify game reviews into positive, negative and neutral ratings with a 55% accuracy.

AB - Opinion mining and sentiment analysis are a trending research domain in Natural Language Processing focused on automatically extracting subjective information, feelings, opinions, ideas or emotions from texts. Our study is centered on identifying sentiments and opinions, as well as other latent linguistic dimensions expressed in on-line game reviews. Over 9500 entertainment game reviews from Amazon were examined using a Principal Component Analysis applied to word-count indices derived from linguistic resources. Eight affective components were identified as being the most representative semantic and sentiment-oriented dimensions for our dataset. These components explained 51.2% of the variance of all reviews. A Multivariate Analysis of Variance showed that five of the eight components demonstrated significant differences between positive, negative and neutral game reviews. These five components used as predictors in a Discriminant Function Analysis, were able to classify game reviews into positive, negative and neutral ratings with a 55% accuracy.

KW - Natural Language Processing

KW - sentiment analysis

KW - opinion mining

KW - game reviews

KW - lexical analysis

U2 - 10.1109/SYNASC.2016.38

DO - 10.1109/SYNASC.2016.38

M3 - Conference Article in proceeding

T3 - SYNASC

SP - 227

EP - 232

BT - SYNASC 2016

A2 - Davenport, James

A2 - Negru, Viorel

A2 - Ida, Tetsuo

A2 - Jebelean, Tudor

A2 - Watt, Stephen

A2 - Zahaire, Daniela

PB - IEEE

T2 - SYNASC 2016

Y2 - 24 September 2016 through 27 September 2016

ER -

Extracting Gamers' Opinions from Reviews

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Projects

Rage: Realising an Applied Gaming Eco-system

Cite this