Statistical comparison of opinion spam detectors in social media with imbalanced datasets

El Sayed M. El-Alfy; Sadam Al-Azani

doi:10.1007/978-981-13-5826-5_12

Statistical comparison of opinion spam detectors in social media with imbalanced datasets

El Sayed M. El-Alfy^*, Sadam Al-Azani

^*Corresponding author for this work

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

2 Scopus citations

Abstract

Sentiment analysis is a growing research area that analyzes people’s opinions towards a specific target using posts shared in social media. However, spammers can inject false opinions to change sentiment-oriented decisions, e.g. low quality products or policies can be promoted or advocated over others. Therefore, identifying and removing spam posts in social media is a crucial data cleaning operation for text mining tasks including sentiment analysis. An inherent problem related to spam detection is the imbalanced-class problem. In this paper, we explore the impact of imbalance ratio on the performance of Twitter spam detection using multiple approaches of single and ensemble classifiers. Besides ensemble-based learning (Bagging and Random forest), we apply the SMOTE oversampling technique to improve detection performance especially for classifiers sensitive to imbalanced datasets.

Original language	English
Title of host publication	Security in Computing and Communications - 6th International Symposium, SSCC 2018, Revised Selected Papers
Editors	Sabu M. Thampi, Danda B. Rawat, Jose M. Alcaraz Calero, Sanjay Madria, Guojun Wang
Publisher	Springer Verlag
Pages	157-167
Number of pages	11
ISBN (Print)	9789811358258
DOIs	https://doi.org/10.1007/978-981-13-5826-5_12
State	Published - 2019

Publication series

Name	Communications in Computer and Information Science
Volume	969
ISSN (Print)	1865-0929

Bibliographical note

Publisher Copyright:
© Springer Nature Singapore Pte Ltd. 2019.

Keywords

Imbalanced dataset
Opinion spam detection
SMOTE
Sentiment analysis
Social big data
Social media security

ASJC Scopus subject areas

General Computer Science
General Mathematics

Access to Document

10.1007/978-981-13-5826-5_12

Cite this

El-Alfy, E. S. M., & Al-Azani, S. (2019). Statistical comparison of opinion spam detectors in social media with imbalanced datasets. In S. M. Thampi, D. B. Rawat, J. M. Alcaraz Calero, S. Madria, & G. Wang (Eds.), Security in Computing and Communications - 6th International Symposium, SSCC 2018, Revised Selected Papers (pp. 157-167). (Communications in Computer and Information Science; Vol. 969). Springer Verlag. https://doi.org/10.1007/978-981-13-5826-5_12

El-Alfy, El Sayed M. ; Al-Azani, Sadam. / Statistical comparison of opinion spam detectors in social media with imbalanced datasets. Security in Computing and Communications - 6th International Symposium, SSCC 2018, Revised Selected Papers. editor / Sabu M. Thampi ; Danda B. Rawat ; Jose M. Alcaraz Calero ; Sanjay Madria ; Guojun Wang. Springer Verlag, 2019. pp. 157-167 (Communications in Computer and Information Science).

@inproceedings{d75ac7340aa24b218dcf234bcb10f996,

title = "Statistical comparison of opinion spam detectors in social media with imbalanced datasets",

abstract = "Sentiment analysis is a growing research area that analyzes people{\textquoteright}s opinions towards a specific target using posts shared in social media. However, spammers can inject false opinions to change sentiment-oriented decisions, e.g. low quality products or policies can be promoted or advocated over others. Therefore, identifying and removing spam posts in social media is a crucial data cleaning operation for text mining tasks including sentiment analysis. An inherent problem related to spam detection is the imbalanced-class problem. In this paper, we explore the impact of imbalance ratio on the performance of Twitter spam detection using multiple approaches of single and ensemble classifiers. Besides ensemble-based learning (Bagging and Random forest), we apply the SMOTE oversampling technique to improve detection performance especially for classifiers sensitive to imbalanced datasets.",

keywords = "Imbalanced dataset, Opinion spam detection, SMOTE, Sentiment analysis, Social big data, Social media security",

author = "El-Alfy, {El Sayed M.} and Sadam Al-Azani",

note = "Publisher Copyright: {\textcopyright} Springer Nature Singapore Pte Ltd. 2019.",

year = "2019",

doi = "10.1007/978-981-13-5826-5_12",

language = "English",

isbn = "9789811358258",

series = "Communications in Computer and Information Science",

publisher = "Springer Verlag",

pages = "157--167",

editor = "Thampi, {Sabu M.} and Rawat, {Danda B.} and {Alcaraz Calero}, {Jose M.} and Sanjay Madria and Guojun Wang",

booktitle = "Security in Computing and Communications - 6th International Symposium, SSCC 2018, Revised Selected Papers",

address = "Germany",

}

El-Alfy, ESM & Al-Azani, S 2019, Statistical comparison of opinion spam detectors in social media with imbalanced datasets. in SM Thampi, DB Rawat, JM Alcaraz Calero, S Madria & G Wang (eds), Security in Computing and Communications - 6th International Symposium, SSCC 2018, Revised Selected Papers. Communications in Computer and Information Science, vol. 969, Springer Verlag, pp. 157-167. https://doi.org/10.1007/978-981-13-5826-5_12

Statistical comparison of opinion spam detectors in social media with imbalanced datasets. / El-Alfy, El Sayed M.; Al-Azani, Sadam.
Security in Computing and Communications - 6th International Symposium, SSCC 2018, Revised Selected Papers. ed. / Sabu M. Thampi; Danda B. Rawat; Jose M. Alcaraz Calero; Sanjay Madria; Guojun Wang. Springer Verlag, 2019. p. 157-167 (Communications in Computer and Information Science; Vol. 969).

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

TY - GEN

T1 - Statistical comparison of opinion spam detectors in social media with imbalanced datasets

AU - El-Alfy, El Sayed M.

AU - Al-Azani, Sadam

N1 - Publisher Copyright: © Springer Nature Singapore Pte Ltd. 2019.

PY - 2019

Y1 - 2019

N2 - Sentiment analysis is a growing research area that analyzes people’s opinions towards a specific target using posts shared in social media. However, spammers can inject false opinions to change sentiment-oriented decisions, e.g. low quality products or policies can be promoted or advocated over others. Therefore, identifying and removing spam posts in social media is a crucial data cleaning operation for text mining tasks including sentiment analysis. An inherent problem related to spam detection is the imbalanced-class problem. In this paper, we explore the impact of imbalance ratio on the performance of Twitter spam detection using multiple approaches of single and ensemble classifiers. Besides ensemble-based learning (Bagging and Random forest), we apply the SMOTE oversampling technique to improve detection performance especially for classifiers sensitive to imbalanced datasets.

AB - Sentiment analysis is a growing research area that analyzes people’s opinions towards a specific target using posts shared in social media. However, spammers can inject false opinions to change sentiment-oriented decisions, e.g. low quality products or policies can be promoted or advocated over others. Therefore, identifying and removing spam posts in social media is a crucial data cleaning operation for text mining tasks including sentiment analysis. An inherent problem related to spam detection is the imbalanced-class problem. In this paper, we explore the impact of imbalance ratio on the performance of Twitter spam detection using multiple approaches of single and ensemble classifiers. Besides ensemble-based learning (Bagging and Random forest), we apply the SMOTE oversampling technique to improve detection performance especially for classifiers sensitive to imbalanced datasets.

KW - Imbalanced dataset

KW - Opinion spam detection

KW - SMOTE

KW - Sentiment analysis

KW - Social big data

KW - Social media security

UR - http://www.scopus.com/inward/record.url?scp=85061154617&partnerID=8YFLogxK

U2 - 10.1007/978-981-13-5826-5_12

DO - 10.1007/978-981-13-5826-5_12

M3 - Conference contribution

AN - SCOPUS:85061154617

SN - 9789811358258

T3 - Communications in Computer and Information Science

SP - 157

EP - 167

BT - Security in Computing and Communications - 6th International Symposium, SSCC 2018, Revised Selected Papers

A2 - Thampi, Sabu M.

A2 - Rawat, Danda B.

A2 - Alcaraz Calero, Jose M.

A2 - Madria, Sanjay

A2 - Wang, Guojun

PB - Springer Verlag

ER -

El-Alfy ESM , Al-Azani S. Statistical comparison of opinion spam detectors in social media with imbalanced datasets. In Thampi SM, Rawat DB, Alcaraz Calero JM, Madria S, Wang G, editors, Security in Computing and Communications - 6th International Symposium, SSCC 2018, Revised Selected Papers. Springer Verlag. 2019. p. 157-167. (Communications in Computer and Information Science). doi: 10.1007/978-981-13-5826-5_12

Statistical comparison of opinion spam detectors in social media with imbalanced datasets

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this