How much do I Stand Out in Communities Q&A? An Analysis of User Interactions based on Graph Embedding

• Paulo Jose de Alcantara Gimenez UNIRIO
• Sean Wolfgand Matsui Siqueira UNIRIO

Resumo

The interactions in Communities Question Answer (CQA) have high dimensionality, generating dispersed and vast information about the users behavior. Understanding this behavior and what characteristics qualify users as the best contributors is still a challenge. In this paper, we rely on Persuasion Theory to identify users who stand out at CQA. We use graph incorporation for reducing data dimensionality to analyze six communities. As a result of the experiments, we found a strong correlation between the intensity of user activity and reputation, but it is not a linear relationship. Also, contrary to the literature, the best contributors are not the top 10-20%, but it varies from community to community. With the results of this work, users can design better strategies for collaboration; headhunters can identify best talents; marketing companies can identify influencers, and developers can adapt their social reputation algorithms.

Palavras-chave: CQA, Q&A, social network analysis, user classification, feature learning

Referências

Hervé Abdi. 2010. Coefficient of variation. Encyclopedia of research design 1 (2010), 169–171.

Mohammed Ali Al-Garadi, Kasturi Dewi Varathan, Sri Devi Ravana, Ejaz Ahmed, Ghulam Mujtaba, Muhammad Usman Shahid Khan, and Samee U Khan. 2018. Analysis of online social network connections for identification of influential users: Survey and open research issues. ACM Computing Surveys (CSUR) 51, 1 (2018), 16. 

Krisztian Balog, Yi Fang, Maarten de Rijke, Pavel Serdyukov, Luo Si, 2012. Expertise retrieval. Foundations and Trends® in Information Retrieval 6, 2–3(2012), 127–256. 

Albert-László Barabási and Réka Albert. 1999. Emergence of scaling in random networks. science 286, 5439 (1999), 509–512.

Clodis Boscarioli, RENATA MENDES DE ARAUJO, and RITA SUZANA PITANGUEIRA MACIEL. 2017. I GranDSI-BR Grand Research Challenges in Information Systems in Brazil 2016-2026. (2017).

Robert B Cialdini and Robert B Cialdini. 1993. Influence: The psychology of persuasion. ” ” 0, 0 (1993), 0.

Mahdi Dehghan and Ahmad Ali Abin. 2019. Translations Diversification for Expert Finding: A Novel Clustering-based Approach. ACM Trans. Knowl. Discov. Data 13, 3, Article 32 (May 2019), 20 pages. https://doi.org/10.1145/3320489

Palash Goyal, Di Huang, Ankita Goswami, Sujit Rokka Chhetri, Arquimedes Canedo, and Emilio Ferrara. 2019. Benchmarks for Graph Embedding Evaluation. arXiv preprint arXiv:1908.06543(2019).

Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 855–864. 

Tao Guan, Le Wang, Jiahua Jin, and Xiaolong Song. 2018. Knowledge contribution behavior in online Q&A communities: An empirical investigation. Computers in Human Behavior 81 (2018), 137–147.

Harry Halpin, Valentin Robu, and Hana Shepard. 2006. The Dynamics and Semantics of Collaborative Tagging.. In SAAW@ ISWC.

Sarah Hayman, IC Schemes, and RW Square. 2007. Folksonomies and tagging. In New Developments in Social Bookmarking, Ark Group Conference: Developing and Improving Classification Schemes, Sydney June. Citeseer.

Sergey Ivanov and Evgeny Burnaev. 2018. Anonymous Walk Embeddings. arxiv:1805.11921 [cs.LG]

Paulo Diogo Rodrigues Leão and Sean Wolfgand Matsui Siqueira. 2019. Structuring a Folksonomy in a Community of Questions and Answers. In 2019 XLV Latin American Computing Conference (CLEI). 1–10. https://doi.org/10.1109/CLEI47609.2019.235090

Sachiko Araki Lira and Anselmo Chaves Neto. 2006. Coeficientes de correlação para variáveis ordinais e dicotômicas derivados do coeficiente linear de Pearson. Ciência & Engenharia 15, 1/2 (2006), 45–53.

Crystiam Kelle Pereira, Jerry Fernandes Medeiros, Sean WM Siqueira, and Bernardo Pereira Nunes. 2019. How complex is the complexity of a concept in exploratory search. In 2019 IEEE 19th International Conference on Advanced Learning Technologies (ICALT), Vol. 2161. IEEE, 17–21.

Crystiam Kelle Pereira, Bernardo Pereira Nunes, Sean WM Siqueira, Ruben Manrique, and Jerry Fernes Medeiros. 2020. ‘A Little Knowledge is a Dangerous Thing’: A method to automatically detect knowledge compartmentalization and oversimplification. In 2020 IEEE 20th International Conference on Advanced Learning Technologies (ICALT). IEEE, 140–144.

Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2014. Deepwalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 701–710. 

Thiago B Procaci, Bernardo Pereira Nunes, Terhi Nurmikko-Fuller, and Sean WM Siqueira. 2016. Finding topical experts in question & answer communities. In 2016 IEEE 16th International Conference on Advanced Learning Technologies (ICALT). IEEE, ” ”, ” ”, 407–411.

Thiago Baesso Procaci, Sean Siqueira, Bernardo Pereira Nunes, and Ujwal Gadiraju. 2019. How Do Outstanding Users Differ From Other Users in Q&A Communities?. In Proceedings of the 30th ACM Conference on Hypertext and Social Media. ACM, ” ”, ” ”, 281–282. 

Thiago Baesso Procaci, Sean WM Siqueira, and Bernardo Pereira Nunes. 2018. Learning in Communities: How Do Outstanding Users Differ From Other Users?. In 2018 IEEE 18th International Conference on Advanced Learning Technologies (ICALT). IEEE, ” ”, ” ”, 173–177. 

Thiago Baesso Procaci, Sean WM Siqueira, and Bernardo Pereira Nunes. 2019. Trust Investigation in Communities Using Feature Learning. In 2019 IEEE 19th International Conference on Advanced Learning Technologies (ICALT), Vol. 2161. IEEE, ” ”, ” ”, 212–216.

Thiago B Procaci, Sean WM Siqueira, Bernardo Pereira Nunes, and Terhi Nurmikko-Fuller. 2017. Modelling experts behaviour in q&a communities to predict worthy discussions. In 2017 IEEE 17th International Conference on Advanced Learning Technologies (ICALT). IEEE, ” ”, ” ”, 291–295.

Thiago Baesso Procaci, Sean Wolfgand Matsui Siqueira, Maria Helena Lima Baptista Braz, and Leila Cristina Vasconcelos de Andrade. 2015. How to find people who can help to answer a question?–Analyses of metrics and machine learning in online communities. Computers in Human Behavior 51 (2015), 664–673. 

Thiago Baesso Procaci, Sean Wolfgand Matsui Siqueira, Bernardo Pereira Nunes, and Terhi Nurmikko-Fuller. 2019. Experts and likely to be closed discussions in question and answer communities: An analytical overview. Computers in Human Behavior 92 (2019), 519–535.

Per Runeson, Martin Host, Austen Rainer, and Bjorn Regnell. 2012. Case study research in software engineering: Guidelines and examples. John Wiley & Sons. 

Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, and Qiaozhu Mei. 2015. Line: Large-scale information network embedding. In Proceedings of the 24th international conference on world wide web. International World Wide Web Conferences Steering Committee, 1067–1077. 

Shuicheng Yan, Dong Xu, Benyu Zhang, Hong-Jiang Zhang, Qiang Yang, and Stephen Lin. 2006. Graph embedding and extensions: A general framework for dimensionality reduction. IEEE transactions on pattern analysis and machine intelligence 29, 1(2006), 40–51. 

Sha Yuan, Yu Zhang, Jie Tang, and Juan Bautista Cabotà. 2018. Expert Finding in Community Question Answering: A Review. arxiv:1804.07958 [cs.IR]

Guoqiang Zhong, Li-Na Wang, Xiao Ling, and Junyu Dong. 2016. An overview on data representation learning: From traditional feature learning to recent deep learning. The Journal of Finance and Data Science 2, 4 (2016), 265–278