How do outstanding users differ from other users in Q&A communities?

Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review

Authors

  • Thiago Baesso Procaci
  • Sean Siqueira
  • Bernardo Pereira Nunes
  • Ujwal Kumar Gadiraju

Research Organisations

External Research Organisations

  • Pontifícia Universidade Católica do Rio de Janeiro (PUC-Rio)
  • Universidade Federal do Rio de Janeiro
View graph of relations

Details

Original languageEnglish
Title of host publicationHT 2019
Subtitle of host publicationProceedings of the 30th ACM Conference on Hypertext and Social Media
Place of PublicationNew York
Pages281-282
Number of pages2
ISBN (electronic)9781450368858
Publication statusPublished - 12 Sept 2019
Event30th ACM Conference on Hypertext and Social Media, HT 2019 - Hof, Germany
Duration: 17 Sept 2019 → 20 Sept 2019

Abstract

This paper reports on an investigation into outstanding and ordinary users of two Question & Answer (Q&A) communities. Considering some behavior perspectives such as participation, linguistic traits, social ties, influence, and focus, we found that outstanding users (i) are more likely to engage in discussions; (ii) tend to use more sophisticated linguistic traits; (iii) generate longer debates; (iv) value the diversity of their connections; and (v) participate in several topics, rather than one specialist niche. These findings allow us to use behavioral patterns to predict if a given user is outstanding and predict which answer gives a definitive solution for a question. Then, we present two feature learning methods to automatically generate the inputs for the prediction model to classify users as outstanding or ordinary. Our feature learning approaches outperformed related methods and generated competitive results when compared to feature engineering based on behavioral patterns.

Keywords

    Graph analysis, Interaction analysis, Learning behavior, Machine learning, Q&A community analysis

ASJC Scopus subject areas

Cite this

How do outstanding users differ from other users in Q&A communities? / Procaci, Thiago Baesso; Siqueira, Sean; Nunes, Bernardo Pereira et al.
HT 2019: Proceedings of the 30th ACM Conference on Hypertext and Social Media. New York, 2019. p. 281-282.

Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review

Procaci, TB, Siqueira, S, Nunes, BP & Gadiraju, UK 2019, How do outstanding users differ from other users in Q&A communities? in HT 2019: Proceedings of the 30th ACM Conference on Hypertext and Social Media. New York, pp. 281-282, 30th ACM Conference on Hypertext and Social Media, HT 2019, Hof, Germany, 17 Sept 2019. https://doi.org/10.1145/3342220.3344928
Procaci, T. B., Siqueira, S., Nunes, B. P., & Gadiraju, U. K. (2019). How do outstanding users differ from other users in Q&A communities? In HT 2019: Proceedings of the 30th ACM Conference on Hypertext and Social Media (pp. 281-282). https://doi.org/10.1145/3342220.3344928
Procaci TB, Siqueira S, Nunes BP, Gadiraju UK. How do outstanding users differ from other users in Q&A communities? In HT 2019: Proceedings of the 30th ACM Conference on Hypertext and Social Media. New York. 2019. p. 281-282 doi: 10.1145/3342220.3344928
Procaci, Thiago Baesso ; Siqueira, Sean ; Nunes, Bernardo Pereira et al. / How do outstanding users differ from other users in Q&A communities?. HT 2019: Proceedings of the 30th ACM Conference on Hypertext and Social Media. New York, 2019. pp. 281-282
Download
@inproceedings{930ad93b03ab4ce584e191f75af18abd,
title = "How do outstanding users differ from other users in Q&A communities?",
abstract = "This paper reports on an investigation into outstanding and ordinary users of two Question & Answer (Q&A) communities. Considering some behavior perspectives such as participation, linguistic traits, social ties, influence, and focus, we found that outstanding users (i) are more likely to engage in discussions; (ii) tend to use more sophisticated linguistic traits; (iii) generate longer debates; (iv) value the diversity of their connections; and (v) participate in several topics, rather than one specialist niche. These findings allow us to use behavioral patterns to predict if a given user is outstanding and predict which answer gives a definitive solution for a question. Then, we present two feature learning methods to automatically generate the inputs for the prediction model to classify users as outstanding or ordinary. Our feature learning approaches outperformed related methods and generated competitive results when compared to feature engineering based on behavioral patterns.",
keywords = "Graph analysis, Interaction analysis, Learning behavior, Machine learning, Q&A community analysis",
author = "Procaci, {Thiago Baesso} and Sean Siqueira and Nunes, {Bernardo Pereira} and Gadiraju, {Ujwal Kumar}",
note = "Funding information: This work was partially supported by the 'National Council for Scientific and Technological Development (CNPq) - Brazil' (Process: 312039/2015-8 - Project: 'Integrating Pedagogical Practices and Methods and Tools of Educational Data Analysis', and Process: 315374/2018-7 - Project: 'Searching as Learning: the information search as a tool for learning').; 30th ACM Conference on Hypertext and Social Media, HT 2019 ; Conference date: 17-09-2019 Through 20-09-2019",
year = "2019",
month = sep,
day = "12",
doi = "10.1145/3342220.3344928",
language = "English",
pages = "281--282",
booktitle = "HT 2019",

}

Download

TY - GEN

T1 - How do outstanding users differ from other users in Q&A communities?

AU - Procaci, Thiago Baesso

AU - Siqueira, Sean

AU - Nunes, Bernardo Pereira

AU - Gadiraju, Ujwal Kumar

N1 - Funding information: This work was partially supported by the 'National Council for Scientific and Technological Development (CNPq) - Brazil' (Process: 312039/2015-8 - Project: 'Integrating Pedagogical Practices and Methods and Tools of Educational Data Analysis', and Process: 315374/2018-7 - Project: 'Searching as Learning: the information search as a tool for learning').

PY - 2019/9/12

Y1 - 2019/9/12

N2 - This paper reports on an investigation into outstanding and ordinary users of two Question & Answer (Q&A) communities. Considering some behavior perspectives such as participation, linguistic traits, social ties, influence, and focus, we found that outstanding users (i) are more likely to engage in discussions; (ii) tend to use more sophisticated linguistic traits; (iii) generate longer debates; (iv) value the diversity of their connections; and (v) participate in several topics, rather than one specialist niche. These findings allow us to use behavioral patterns to predict if a given user is outstanding and predict which answer gives a definitive solution for a question. Then, we present two feature learning methods to automatically generate the inputs for the prediction model to classify users as outstanding or ordinary. Our feature learning approaches outperformed related methods and generated competitive results when compared to feature engineering based on behavioral patterns.

AB - This paper reports on an investigation into outstanding and ordinary users of two Question & Answer (Q&A) communities. Considering some behavior perspectives such as participation, linguistic traits, social ties, influence, and focus, we found that outstanding users (i) are more likely to engage in discussions; (ii) tend to use more sophisticated linguistic traits; (iii) generate longer debates; (iv) value the diversity of their connections; and (v) participate in several topics, rather than one specialist niche. These findings allow us to use behavioral patterns to predict if a given user is outstanding and predict which answer gives a definitive solution for a question. Then, we present two feature learning methods to automatically generate the inputs for the prediction model to classify users as outstanding or ordinary. Our feature learning approaches outperformed related methods and generated competitive results when compared to feature engineering based on behavioral patterns.

KW - Graph analysis

KW - Interaction analysis

KW - Learning behavior

KW - Machine learning

KW - Q&A community analysis

UR - http://www.scopus.com/inward/record.url?scp=85073387677&partnerID=8YFLogxK

U2 - 10.1145/3342220.3344928

DO - 10.1145/3342220.3344928

M3 - Conference contribution

AN - SCOPUS:85073387677

SP - 281

EP - 282

BT - HT 2019

CY - New York

T2 - 30th ACM Conference on Hypertext and Social Media, HT 2019

Y2 - 17 September 2019 through 20 September 2019

ER -