An answerer recommendation approach on Stack Overflow using Historical Posts with User Profile Data
Loading...
Date
Journal Title
Journal ISSN
Volume Title
Publisher
Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh
Abstract
The exponential growth of community-driven knowledge platforms such as Stack
Overflow has created a pressing need for effective recommendation systems that can
personalize content to users expertise and interests. This thesis presents a hybrid
recommendation approach that integrates semantic topic embeddings, temporal ac
tiveness features, and reputation-based contribution metrics into a unified two-tower
neural recommendation framework.
To address the challenge of high-dimensional and composite tag vocabularies, a pre
processing strategywasdevelopedtoadaptpretrainedtopicembeddingstoover10,000
StackOverflow tags, including hyphenated and dot-separated forms. User represen
tations were constructed by aggregating embeddings of interacted tags, augmented
with features derived from activity patterns and reputation dynamics. Negative sam
pling was employed using cosine similarity thresholds to differentiate relevant from
irrelevant tags, while candidate sampling ensured balanced evaluation across users.
Experimental results across multiple configurations demonstrate that topic embed
dings provide a strong semantic baseline, but recommendation quality does not im
prove with the addition of activeness and contribution features. The contribution of
this paper is an empirical insight that semantic topic signals dominate, and adding
activeness and reputational features naively reducesperformance. Thefindingiscon
tradictory to the assumptions of other papers, such as IEA [22], on the fact that using
different types of features improves the result
Description
Supervised by
Mr. Shohel Ahmed,
Assistant Professor,
Department of Computer Science and Engineering (CSE)
Islamic University of Technology (IUT)
Board Bazar, Gazipur, Bangladesh
This thesis is submitted in partial fulfillment of the requirement for the degree of Bachelor of Science in Software Engineering, 2025
Keywords
Citation
[1] M.-F. Chiang, W.-C. Peng, and P. S. Yu, “Exploring latent browsing graph for question answering recommendation,” WorldWideWeb,vol.15,no.5,pp.603 630, 2012. [2] H. Dong, J. Wang, H. Lin, B. Xu, and Z. Yang, “Predicting best answerers for new questions: An approach leveraging distributed representations of words in community question answering,” in 2015 Ninth international conference on frontier of computer science and technology, IEEE, 2015, pp. 13–18. [3] V.Efstathiou, C. Chatzilenas, and D. Spinellis, “Word embeddings for the soft ware engineering domain,” in Proceedings of the 15th international conference on mining software repositories, 2018, pp. 38–41. [4] J. Guo, S. Xu, S. Bao, and Y. Yu, “Tapping on the potential of q&a community byrecommendinganswerproviders,”inProceedingsofthe17thACMconference on Information and knowledge management, 2008, pp. 921–930. [5] B. V. Hanrahan, G. Convertino, and L. Nelson, “Modeling problem difficulty and expertise in stackoverflow,” in Proceedings of the ACM 2012 conference on computer supported cooperative work companion, 2012, pp. 91–94. [6] Y.Hu,Y. Koren, and C. Volinsky, “Collaborative filtering for implicit feedback datasets,” in 2008 Eighth IEEE international conference on data mining, Ieee, 2008, pp. 263–272. [7] C.Huang, L. Yao, X. Wang, B. Benatallah, and X. Zhang, “Software expert dis covery via knowledge domain embeddings in a collaborative network,” Pattern Recognition Letters, vol. 130, pp. 46–53, 2020. [8] P. Jurczyk and E. Agichtein, “Hits on question answer portals: Exploration of link analysis for authorranking,”inProceedingsofthe30thannualinternational ACM SIGIR conference on Research and development in information retrieval, 2007, pp. 845–846. [9] Q.LeandT.Mikolov,“Distributedrepresentationsofsentencesanddocuments,” in International conference on machine learning, PMLR, 2014, pp. 1188–1196. 40 [10] Z. Li, J.-Y. Jiang, Y. Sun, and W. Wang, “Personalized question routing via het erogeneous network embedding,” in Proceedings of the AAAI conference on ar tificial intelligence, vol. 33, 2019, pp. 192–199. [11] S. Liang and M. De Rijke, “Formal language models for finding groups of ex perts,” Information Processing & Management, vol. 52, no. 4, pp. 529–549, 2016. [12] Z.Meng,F.Gandon,andC.F.Zucker,“Jointmodeloftopics,expertises, activi ties and trendsforquestionansweringwebapplications,”in2016IEEE/WIC/ACM International Conference on Web Intelligence (WI), IEEE, 2016, pp. 296–303. [13] T. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” arXiv preprint arXiv:1301.3781, 2013. [14] X. Qiu and X. Huang, “Convolutional neural tensor network architecture for community-based question answering.,” in Ijcai, vol. 15, 2015, pp. 1305–1311. [15] F. Riahi, Z. Zolaktaf, M. Shafiei, and E. Milios, “Finding expert users in com munity question answering,” in Proceedings of the 21st international conference on world wide web, 2012, pp. 791–798. [16] S.Robertson,H.Zaragoza,etal.,“Theprobabilisticrelevanceframework:Bm25 and beyond,” Foundations and Trendső in Information Retrieval, vol. 3, no. 4, pp. 333–389, 2009. [17] P. K. Roy and J. P. Singh, “Early prediction of promising expert users on com munity question answering sites,” International Journal of System Assurance Engineering and Management, vol. 15, no. 7, pp. 2902–2913, 2024. [18] R. Salakhutdinov, A. Mnih, and G. Hinton, “Restricted boltzmann machines for collaborative filtering,” in Proceedings of the 24th international conference on Machine learning, 2007, pp. 791–798. [19] StackOverflow,Stackoverflow,StackExchangeInc.RetrievedOctober20,2025, from https://stackoverflow.com, n.d. [20] StackOverflow,Whataretags,andhowshouldiusethem? StackOverflowHelp Center.RetrievedOctober20,2025,fromhttps://stackoverflow.com/help/ tagging, n.d. [21] D. Van Dijk, M. Tsagkias, and M. De Rijke, “Early detection of topical exper tise in community question answering,” in Proceedingsofthe38thinternational ACM SIGIR conference on research and development in information retrieval, 2015, pp. 995–998. 41 [22] L.Wang,L. Zhang, and J. Jiang, “Iea: An answerer recommendation approach on stack overflow,” Science China Information Sciences, vol. 62, pp. 1–19, 2019. [23] J. Wei, J. He, K. Chen, Y. Zhou, and Z. Tang, “Collaborative filtering and deep learning based recommendation system for cold start items,” Expert systems with applications, vol. 69, pp. 29–39, 2017. [24] L. Wu,R.Wang,L. Su, and J. Li, “A study of expert finding methods for multi granularity encoded community question answering by fusing graph neural networks,” IEEE Access, 2024. [25] L.Yangetal.,“Cqarank:Jointlymodeltopicsandexpertiseincommunityques tion answering,” in Proceedings of the 22nd ACM international conference on Information & Knowledge Management, 2013, pp. 99–108. [26] H. Ying, L. Chen, Y. Xiong, and J. Wu, “Collaborative deep ranking: A hybrid pair-wise recommendation algorithm with implicit feedback,” in Pacific-asia conference on knowledge discovery and data mining, Springer, 2016, pp. 555 567. [27] S.Yuan,Y.Zhang,J.Tang,W.Hall,andJ.B.Cabotà,“Expertfindingincommu nity question answering: A review,” Artificial Intelligence Review, vol. 53, no. 2, pp. 843–874, 2020. [28] J. Zhang, M. S. Ackerman, and L. Adamic, “Expertise networks in online com munities: Structure and algorithms,” in Proceedings of the 16th international conference on World Wide Web, 2007, pp. 221–230