High Resolution Sentiment Analysis by Ensemble Classification

Jordan J. Bird; Anikó Ekárt; Christopher D. Buckingham; Diego R. Faria

doi:10.1007/978-3-030-22871-2_40

High Resolution Sentiment Analysis by Ensemble Classification

Jordan J. Bird^*
, Anikó Ekárt
, Christopher D. Buckingham
, Diego R. Faria

^*Corresponding author for this work

Research output: Chapter in Book/Published conference output › Conference publication

11 Citations (Scopus)

Abstract

This study proposes an approach to ensemble sentiment classification of a text to a score in the range of 1–5 of negative-positive scoring. A high-performing model is produced from TripAdvisor restaurant reviews via a generated dataset of 684 word-stems, gathered by information gain attribute selection from the entire corpus. The best performing classification was an ensemble classifier of RandomForest, Naive Bayes Multinomial and Multilayer Perceptron (Neural Network) methods ensembled via a Vote on Average Probabilities approach. The best ensemble produced a classification accuracy of 91.02% which scored higher than the best single classifier, a Random Tree model with an accuracy of 78.6%. Other ensembles through Adaptive Boosting, Random Forests and Voting are explored with ten-fold cross-validation. All ensemble methods far outperformed the best single classifier methods. Even though extremely high results are achieved, analysis documents the few mis-classified instances as almost entirely being close to their real class via the model’s given error matrix.

Original language	English
Title of host publication	Intelligent Computing - Proceedings of the 2019 Computing Conference
Editors	Kohei Arai, Rahul Bhatia, Supriya Kapoor
Publisher	Springer
Pages	593-606
Number of pages	14
ISBN (Print)	9783030228705
DOIs	https://doi.org/10.1007/978-3-030-22871-2_40
Publication status	Published - 23 Jun 2019
Event	Computing Conference, 2019 - London, United Kingdom Duration: 16 Jul 2019 → 17 Jul 2019

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	997
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	Computing Conference, 2019
Country/Territory	United Kingdom
City	London
Period	16/07/19 → 17/07/19

Funding

Acknowledgments. This work was supported by the European Commission through the H2020 project EXCELL (https://www.excell-project.eu/), grant No. 691829. This work was also partially supported by the EIT Health GRaCEAGE grant number 18429 awarded to C.D. Buckingham.

Keywords

Classification
Ensemble learning
Machine learning
Opinion mining
Sentiment analysis

Access to Document

10.1007/978-3-030-22871-2_40

Cite this

Bird, J. J., Ekárt, A., Buckingham, C. D., & Faria, D. R. (2019). High Resolution Sentiment Analysis by Ensemble Classification. In K. Arai, R. Bhatia, & S. Kapoor (Eds.), Intelligent Computing - Proceedings of the 2019 Computing Conference (pp. 593-606). (Advances in Intelligent Systems and Computing; Vol. 997). Springer. https://doi.org/10.1007/978-3-030-22871-2_40

@inproceedings{317cf5a417b343f49c58317cdc532dd7,

title = "High Resolution Sentiment Analysis by Ensemble Classification",

abstract = "This study proposes an approach to ensemble sentiment classification of a text to a score in the range of 1–5 of negative-positive scoring. A high-performing model is produced from TripAdvisor restaurant reviews via a generated dataset of 684 word-stems, gathered by information gain attribute selection from the entire corpus. The best performing classification was an ensemble classifier of RandomForest, Naive Bayes Multinomial and Multilayer Perceptron (Neural Network) methods ensembled via a Vote on Average Probabilities approach. The best ensemble produced a classification accuracy of 91.02\% which scored higher than the best single classifier, a Random Tree model with an accuracy of 78.6\%. Other ensembles through Adaptive Boosting, Random Forests and Voting are explored with ten-fold cross-validation. All ensemble methods far outperformed the best single classifier methods. Even though extremely high results are achieved, analysis documents the few mis-classified instances as almost entirely being close to their real class via the model{\textquoteright}s given error matrix.",

keywords = "Classification, Ensemble learning, Machine learning, Opinion mining, Sentiment analysis",

author = "Bird, \{Jordan J.\} and Anik{\'o} Ek{\'a}rt and Buckingham, \{Christopher D.\} and Faria, \{Diego R.\}",

year = "2019",

month = jun,

day = "23",

doi = "10.1007/978-3-030-22871-2\_40",

language = "English",

isbn = "9783030228705",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer",

pages = "593--606",

editor = "Kohei Arai and Rahul Bhatia and Supriya Kapoor",

booktitle = "Intelligent Computing - Proceedings of the 2019 Computing Conference",

address = "Germany",

note = "Computing Conference, 2019 ; Conference date: 16-07-2019 Through 17-07-2019",

}

Bird, JJ, Ekárt, A , Buckingham, CD & Faria, DR 2019, High Resolution Sentiment Analysis by Ensemble Classification. in K Arai, R Bhatia & S Kapoor (eds), Intelligent Computing - Proceedings of the 2019 Computing Conference. Advances in Intelligent Systems and Computing, vol. 997, Springer, pp. 593-606, Computing Conference, 2019, London, United Kingdom, 16/07/19. https://doi.org/10.1007/978-3-030-22871-2_40

High Resolution Sentiment Analysis by Ensemble Classification. / Bird, Jordan J.; Ekárt, Anikó ; Buckingham, Christopher D. et al.
Intelligent Computing - Proceedings of the 2019 Computing Conference. ed. / Kohei Arai; Rahul Bhatia; Supriya Kapoor. Springer, 2019. p. 593-606 (Advances in Intelligent Systems and Computing; Vol. 997).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - High Resolution Sentiment Analysis by Ensemble Classification

AU - Bird, Jordan J.

AU - Ekárt, Anikó

AU - Buckingham, Christopher D.

AU - Faria, Diego R.

PY - 2019/6/23

Y1 - 2019/6/23

N2 - This study proposes an approach to ensemble sentiment classification of a text to a score in the range of 1–5 of negative-positive scoring. A high-performing model is produced from TripAdvisor restaurant reviews via a generated dataset of 684 word-stems, gathered by information gain attribute selection from the entire corpus. The best performing classification was an ensemble classifier of RandomForest, Naive Bayes Multinomial and Multilayer Perceptron (Neural Network) methods ensembled via a Vote on Average Probabilities approach. The best ensemble produced a classification accuracy of 91.02% which scored higher than the best single classifier, a Random Tree model with an accuracy of 78.6%. Other ensembles through Adaptive Boosting, Random Forests and Voting are explored with ten-fold cross-validation. All ensemble methods far outperformed the best single classifier methods. Even though extremely high results are achieved, analysis documents the few mis-classified instances as almost entirely being close to their real class via the model’s given error matrix.

AB - This study proposes an approach to ensemble sentiment classification of a text to a score in the range of 1–5 of negative-positive scoring. A high-performing model is produced from TripAdvisor restaurant reviews via a generated dataset of 684 word-stems, gathered by information gain attribute selection from the entire corpus. The best performing classification was an ensemble classifier of RandomForest, Naive Bayes Multinomial and Multilayer Perceptron (Neural Network) methods ensembled via a Vote on Average Probabilities approach. The best ensemble produced a classification accuracy of 91.02% which scored higher than the best single classifier, a Random Tree model with an accuracy of 78.6%. Other ensembles through Adaptive Boosting, Random Forests and Voting are explored with ten-fold cross-validation. All ensemble methods far outperformed the best single classifier methods. Even though extremely high results are achieved, analysis documents the few mis-classified instances as almost entirely being close to their real class via the model’s given error matrix.

KW - Classification

KW - Ensemble learning

KW - Machine learning

KW - Opinion mining

KW - Sentiment analysis

UR - https://www.scopus.com/pages/publications/85069154045

UR - https://link.springer.com/chapter/10.1007%2F978-3-030-22871-2_40

U2 - 10.1007/978-3-030-22871-2_40

DO - 10.1007/978-3-030-22871-2_40

M3 - Conference publication

AN - SCOPUS:85069154045

SN - 9783030228705

T3 - Advances in Intelligent Systems and Computing

SP - 593

EP - 606

BT - Intelligent Computing - Proceedings of the 2019 Computing Conference

A2 - Arai, Kohei

A2 - Bhatia, Rahul

A2 - Kapoor, Supriya

PB - Springer

T2 - Computing Conference, 2019

Y2 - 16 July 2019 through 17 July 2019

ER -

High Resolution Sentiment Analysis by Ensemble Classification

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this