User Modeling on Twitter with Exploiting Explicit Relationships for Personalized Recommendations

Abduallah Alshammari, Stelios Kapetanakis, Roger Evans, Nikolaos Polatidis, Gharbi Alshammari

Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBNResearchpeer-review

Abstract

The use of social networks sites has led to a challenging overload of information that helped new social networking sites such as Twitter to become popular. It is believed that Twitter provides a rich environment for shared information that can help with recommender systems research. In this paper, we study Twitter user modeling by utilizing explicit relationships among users. This work aims to build personal profiles through a alternative methods using information gained from Twitter to provide more accurate recommendations. Our method exploits the explicit relationships of a Twitter user to extract information that is important in building the user’s personal profile. The usefulness of this proposed method is validated by implementing a tweet recommendation service and by performing offline evaluation. We compare our proposed user profiles against other profiles such as a baseline using cosine similarity measures to check the effectiveness of the proposed method. The performance is measured on an adequate number of users.

Original languageEnglish
Title of host publicationHybrid Intelligent Systems - 18th International Conference on Hybrid Intelligent Systems HIS 2018
EditorsMaria Leonilde Varela, Ajith Abraham, Niketa Gandhi, Ana Maria Madureira
Place of PublicationCham
PublisherSpringer
Pages135-145
Number of pages11
Volume923
ISBN (Electronic)9783030143473
ISBN (Print)9783030143466
DOIs
Publication statusPublished - 21 Mar 2019

Publication series

NameAdvances in Intelligent Systems and Computing
Volume923
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Fingerprint

Recommender systems

Keywords

  • Explicit relationships
  • Influence score
  • Recommender systems
  • Twitter
  • User modeling
  • User profiling

Cite this

Alshammari, A., Kapetanakis, S., Evans, R., Polatidis, N., & Alshammari, G. (2019). User Modeling on Twitter with Exploiting Explicit Relationships for Personalized Recommendations. In M. L. Varela, A. Abraham, N. Gandhi, & A. M. Madureira (Eds.), Hybrid Intelligent Systems - 18th International Conference on Hybrid Intelligent Systems HIS 2018 (Vol. 923, pp. 135-145). (Advances in Intelligent Systems and Computing; Vol. 923). Cham: Springer. https://doi.org/10.1007/978-3-030-14347-3_14
Alshammari, Abduallah ; Kapetanakis, Stelios ; Evans, Roger ; Polatidis, Nikolaos ; Alshammari, Gharbi. / User Modeling on Twitter with Exploiting Explicit Relationships for Personalized Recommendations. Hybrid Intelligent Systems - 18th International Conference on Hybrid Intelligent Systems HIS 2018. editor / Maria Leonilde Varela ; Ajith Abraham ; Niketa Gandhi ; Ana Maria Madureira. Vol. 923 Cham : Springer, 2019. pp. 135-145 (Advances in Intelligent Systems and Computing).
@inproceedings{86b482a9b71948b3a375efe37b29c248,
title = "User Modeling on Twitter with Exploiting Explicit Relationships for Personalized Recommendations",
abstract = "The use of social networks sites has led to a challenging overload of information that helped new social networking sites such as Twitter to become popular. It is believed that Twitter provides a rich environment for shared information that can help with recommender systems research. In this paper, we study Twitter user modeling by utilizing explicit relationships among users. This work aims to build personal profiles through a alternative methods using information gained from Twitter to provide more accurate recommendations. Our method exploits the explicit relationships of a Twitter user to extract information that is important in building the user’s personal profile. The usefulness of this proposed method is validated by implementing a tweet recommendation service and by performing offline evaluation. We compare our proposed user profiles against other profiles such as a baseline using cosine similarity measures to check the effectiveness of the proposed method. The performance is measured on an adequate number of users.",
keywords = "Explicit relationships, Influence score, Recommender systems, Twitter, User modeling, User profiling",
author = "Abduallah Alshammari and Stelios Kapetanakis and Roger Evans and Nikolaos Polatidis and Gharbi Alshammari",
year = "2019",
month = "3",
day = "21",
doi = "10.1007/978-3-030-14347-3_14",
language = "English",
isbn = "9783030143466",
volume = "923",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer",
pages = "135--145",
editor = "Varela, {Maria Leonilde} and Ajith Abraham and Niketa Gandhi and Madureira, {Ana Maria}",
booktitle = "Hybrid Intelligent Systems - 18th International Conference on Hybrid Intelligent Systems HIS 2018",

}

Alshammari, A, Kapetanakis, S, Evans, R, Polatidis, N & Alshammari, G 2019, User Modeling on Twitter with Exploiting Explicit Relationships for Personalized Recommendations. in ML Varela, A Abraham, N Gandhi & AM Madureira (eds), Hybrid Intelligent Systems - 18th International Conference on Hybrid Intelligent Systems HIS 2018. vol. 923, Advances in Intelligent Systems and Computing, vol. 923, Springer, Cham, pp. 135-145. https://doi.org/10.1007/978-3-030-14347-3_14

User Modeling on Twitter with Exploiting Explicit Relationships for Personalized Recommendations. / Alshammari, Abduallah ; Kapetanakis, Stelios; Evans, Roger; Polatidis, Nikolaos; Alshammari, Gharbi.

Hybrid Intelligent Systems - 18th International Conference on Hybrid Intelligent Systems HIS 2018. ed. / Maria Leonilde Varela; Ajith Abraham; Niketa Gandhi; Ana Maria Madureira. Vol. 923 Cham : Springer, 2019. p. 135-145 (Advances in Intelligent Systems and Computing; Vol. 923).

Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBNResearchpeer-review

TY - GEN

T1 - User Modeling on Twitter with Exploiting Explicit Relationships for Personalized Recommendations

AU - Alshammari, Abduallah

AU - Kapetanakis, Stelios

AU - Evans, Roger

AU - Polatidis, Nikolaos

AU - Alshammari, Gharbi

PY - 2019/3/21

Y1 - 2019/3/21

N2 - The use of social networks sites has led to a challenging overload of information that helped new social networking sites such as Twitter to become popular. It is believed that Twitter provides a rich environment for shared information that can help with recommender systems research. In this paper, we study Twitter user modeling by utilizing explicit relationships among users. This work aims to build personal profiles through a alternative methods using information gained from Twitter to provide more accurate recommendations. Our method exploits the explicit relationships of a Twitter user to extract information that is important in building the user’s personal profile. The usefulness of this proposed method is validated by implementing a tweet recommendation service and by performing offline evaluation. We compare our proposed user profiles against other profiles such as a baseline using cosine similarity measures to check the effectiveness of the proposed method. The performance is measured on an adequate number of users.

AB - The use of social networks sites has led to a challenging overload of information that helped new social networking sites such as Twitter to become popular. It is believed that Twitter provides a rich environment for shared information that can help with recommender systems research. In this paper, we study Twitter user modeling by utilizing explicit relationships among users. This work aims to build personal profiles through a alternative methods using information gained from Twitter to provide more accurate recommendations. Our method exploits the explicit relationships of a Twitter user to extract information that is important in building the user’s personal profile. The usefulness of this proposed method is validated by implementing a tweet recommendation service and by performing offline evaluation. We compare our proposed user profiles against other profiles such as a baseline using cosine similarity measures to check the effectiveness of the proposed method. The performance is measured on an adequate number of users.

KW - Explicit relationships

KW - Influence score

KW - Recommender systems

KW - Twitter

KW - User modeling

KW - User profiling

UR - http://www.scopus.com/inward/record.url?scp=85064884712&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-14347-3_14

DO - 10.1007/978-3-030-14347-3_14

M3 - Conference contribution with ISSN or ISBN

SN - 9783030143466

VL - 923

T3 - Advances in Intelligent Systems and Computing

SP - 135

EP - 145

BT - Hybrid Intelligent Systems - 18th International Conference on Hybrid Intelligent Systems HIS 2018

A2 - Varela, Maria Leonilde

A2 - Abraham, Ajith

A2 - Gandhi, Niketa

A2 - Madureira, Ana Maria

PB - Springer

CY - Cham

ER -

Alshammari A, Kapetanakis S, Evans R, Polatidis N, Alshammari G. User Modeling on Twitter with Exploiting Explicit Relationships for Personalized Recommendations. In Varela ML, Abraham A, Gandhi N, Madureira AM, editors, Hybrid Intelligent Systems - 18th International Conference on Hybrid Intelligent Systems HIS 2018. Vol. 923. Cham: Springer. 2019. p. 135-145. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-030-14347-3_14