Predicting Question Popularity for Community Question Answering
Abstract
:1. Introduction
- All these temporal point process models do not take into account the impact of user interaction on an event cascade in the online community. An important feature of the online community is that people can interact with others anytime, anywhere. For instance, in CQA, users can vote for their favorite answers or leave their own opinions in the comments section. These interactions will affect the ranking of the answers. Figure 1 shows answers of a question related to interpersonal socialization in Zhihu, which is a famous Chinese Community Question Answering platform. As we can see, top-ranked answers, though they were posed a long time ago (four years before), received more than 10k thumbs-up votes, so they were ranked ahead. In contrast, new answers received a small number of votes, and thus they are ranked at the bottom and unobserved at the top. It is generally believed that the impact of recent events in the future is greater than that of past events [8,9,10], but due to the special interaction mechanism in CQA, a long-term but high-quality answer will gain users’ attention because of the higher ranking, which will have a lasting and important impact on the future of a question.
- There is an obvious Matthew effect [11] in CQA, which has not been considered in previous models. The Matthew effect is a concept originating in the biblical Gospel of Matthew. It is sometimes summarized by the adage “the rich get richer, while the poor get poorer”. Robert Merton, a sociologist, first observed the Matthew effect in the academic field in that eminent scientists will often receive more credit than a comparatively unknown researcher even if their works are similar. The Matthew effect has been found in many aspects of our social life [12,13,14,15,16,17,18].In CQA, this effect is very common and is amplified by answer visibilities. The rapid development of online social media has brought about the outbreak of information. However, people are usually only attracted by a few top-rank high-quality answers, while the rest go unnoticed [19]. Moreover, these excellent answers will accumulate advantages, while a higher ranking makes them easier to attract users’ attention and obtain a better ranking. Due to the existence of the Matthew effect, an early dominant answer will continue to widen the gap with other answers. As shown in Figure 1, the number of votes for the first answer is nearly five times more than that of the second answer. The Matthew effect affects the ranking of answers, and ranking affects the users’ first impression of a question, which in turn affects the popularity of the question. However, existing approaches do not take into account this common phenomenon in CQA.
- For the convenience of analyzing information diffusion, with very few exceptions [8,20,21], most existing point process models make specific assumptions about the functional forms of the underlying generative processes. For example, the Hawkes process [22,23,24], a famous non-homogenous Poisson process, supposes that the arrival of an event causes the probability of future events to increase, assuming that historical events influence future events through a positive, additive and time decay kernel function. However, the true mechanism behind event cascade is hard to specify or verify in practice, and thus, the fixed simple parametric representations may constrain the expressive power of these models.
- We propose a Posterior Attention Recurrent Point Process Model, PARPP, to predict the popularity of questions in CQA. Our PARPP is a new point process model that takes into account the impact of user interaction in the modeling of the point process.
- In CQA, users’ interactions will affect the ranking of the answers and thus the popularity of the question. Our proposed PARPP fully utilizes users’ interactions by a posterior attention mechanism.
- We explore the Matthew effect existing in CQA, such that a higher praised answer will accumulate advantages and gain more attention from users. To our knowledge, we are the first to study the Matthew effect in CQA.
- To model the Matthew effect, we further introduce a convergence strategy in the proposed attention-based model that yields better prediction performance.
- Our proposed model, PARPP, yields powerful results compared to existing state-of-the-art methods in two cascade prediction tasks. The analysis of the experimental results shows that the learned alignments in our model can accurately capture the changes of users’ attention to different answers over time.
2. Related Work
2.1. Community Question Answering
2.2. Cascade Prediction
2.3. Point Process
2.4. Attention Mechanism
2.5. Matthew Effect
3. Model
3.1. Problem Formulation
- Predicting Questions’ Popularities in CQA. Given a question-answering history , the goal is to seek a function f that aims at predicting the time of the next answer and predicting the number of answers at the future time :
3.2. Temporal Point Process
3.3. Recurrent Point Process
3.4. Attention Mechanism
3.5. Convergence Strategy
3.6. Parameter Learning
4. Experimental Setup
4.1. Research Questions
- (RQ1) Given a question and the trace of observed answers, when will the next answer appear?
- (RQ2) Given a question and the trace of observed answers, how many answers will be posted in the future?
- (RQ3) Can the proposed attention mechanism capture the most influential answers?
4.2. Dataset
4.3. Matthew Effect in CQA
4.4. Baselines
- Naive Prediction. This is a naive baseline that uses the time difference between the last two answeres to predict when the next answer will appear.
- Poisson Process [85]. This is a point process that assumes the conditional intensity function is independent of the history and remains constant over time:
- Hawkes Process [86]. This is a self-exciting process in which the arrival of an event causes the conditional intensity function to increase. The intensity function is parameterized by
- RMTPP [59]. The recurrent marked temporal point process (RMTPP) is a temporal point processes method based on the RNN. The original model not only predicts the time of the next event but also predicts the type of the next event. Here, we only use it to predict the next time. Specifically, RMTPP applies an RNN to learn a general representation of a nonlinear dependency over both the time and the marker information from past events:
- CYAN-RNN [8]. This is an attention-based RNN method to model cascade dynamics. Similarly, the conditional intensity function is computed byThe author [8] further proposed a coverage strategy to adjust the misallocation of attention. We denote CYAN-RNN with coverage as CYAN-RNN(cov).
4.5. Evaluation Metrics
- RMSE. Every time we make a prediction, we have an estimate . We can obtain RMSE for time prediction by
- MAPE. reports the mean deviation of the estimated timestamps of the next future events from their actual times:
- Mean Absolute Error per Day: This indicator can measure the impact of forecast duration on forecast results and is defined as follows:
- Precision. Precision is a widely used metric to judge whether a model can correctly predict the positive samples. We calculate how many answers are in both the set and the ground-truth set and treat them as true positive. We calculate P@k as shown below:
- NDCG. Because P@k does not consider the ranking position, we also use NDCG@k. We denote as the i-th answer in and define the relevance () of as follows:
5. Results and Analysis
5.1. Predict the Time of the Next Answer
5.2. Predict the Number of Answers
5.3. Evaluation on Attention Mechanism
6. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Roy, P.K.; Saumya, S.; Singh, J.P.; Banerjee, S.; Gutub, A. Analysis of community question-answering issues via machine learning and deep learning: State-of-the-art review. CAAI Trans. Intell. Technol. 2023, 8, 95–117. [Google Scholar] [CrossRef]
- Kandpal, N.; Deng, H.; Roberts, A.; Wallace, E.; Raffel, C. Large language models struggle to learn long-tail knowledge. In Proceedings of the International Conference on Machine Learning, Honolulu, HI, USA, 23–29 July 2023; pp. 15696–15707. [Google Scholar]
- Wang, Y.; Lipka, N.; Rossi, R.A.; Siu, A.; Zhang, R.; Derr, T. Knowledge graph prompting for multi-document question answering. In Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada, 20–28 February 2024; Volume 38, pp. 19206–19214. [Google Scholar]
- Wu, Y.; Fu, Y.; Xu, J.; Yin, H.; Zhou, Q.; Liu, D. Heterogeneous question answering community detection based on graph neural network. Inf. Sci. 2023, 621, 652–671. [Google Scholar] [CrossRef]
- Annamoradnejad, I.; Habibi, J. Automatic Moderation of User-Generated Content. In Encyclopedia of Data Science and Machine Learning; IGI Global: Hershey, PA, USA, 2023; pp. 1344–1355. [Google Scholar]
- Liu, T.; Zhang, W.N.; Cao, L.; Zhang, Y. Question popularity analysis and prediction in community question answering services. PLoS ONE 2014, 9, e85236. [Google Scholar] [CrossRef] [PubMed]
- Wu, Y.; Yin, H.; Zhou, Q.; Liu, D.; Wei, D.; Dong, J. Multi-hop community question answering based on multi-aspect heterogeneous graph. Inf. Process. Manag. 2024, 61, 103543. [Google Scholar] [CrossRef]
- Wang, Y.; Shen, H.; Liu, S.; Gao, J.; Cheng, X. Cascade Dynamics Modeling with Attention-based Recurrent Neural Network. In Proceedings of the IJCAI, Melbourne, Australia, 19–25 August 2017; pp. 2985–2991. [Google Scholar]
- Embrechts, P.; Liniger, T.; Lin, L. Multivariate Hawkes processes: An application to financial data. J. Appl. Probab. 2011, 48, 367–378. [Google Scholar] [CrossRef]
- Rizoiu, M.A.; Xie, L.; Sanner, S.; Cebrian, M.; Yu, H.; Van Hentenryck, P. Expecting to be hip: Hawkes intensity processes for social media popularity. In Proceedings of the 26th International World Wide Web Conferences Steering Committee, Perth, Australia, 3–7 May 2017; pp. 735–744. [Google Scholar]
- Merton, R.K. The Matthew effect in science: The reward and communication systems of science are considered. Science 1968, 159, 56–63. [Google Scholar] [CrossRef] [PubMed]
- Liao, C.H. The Matthew effect and the halo effect in research funding. J. Inf. 2021, 15, 101108. [Google Scholar] [CrossRef]
- Liu, M.; Li, S.; Jin, L. Modeling and analysis of Matthew effect under switching social networks via distributed competition. IEEE/CAA J. Autom. Sin. 2022, 9, 1311–1314. [Google Scholar] [CrossRef]
- Saez, E.; Zucman, G. Exploding Wealth Inequality in the United States; Washington Center for Equitable Growth: Washington, DC, USA, 2014. [Google Scholar]
- Bol, T.; de Vaan, M.; van de Rijt, A. The Matthew effect in science funding. Proc. Natl. Acad. Sci. USA 2018, 115, 4887–4890. [Google Scholar] [CrossRef]
- Pavolini, E.; Van Lancker, W. The Matthew effect in childcare use: A matter of policies or preferences? J. Eur. Public Policy 2018, 25, 878–893. [Google Scholar] [CrossRef]
- Wan, Y. The Matthew effect in social commerce. Electron. Mark. 2015, 25, 313–324. [Google Scholar] [CrossRef]
- Tang, T.L.P. The Matthew Effect in monetary wisdom. In Monetary Wisdom; Academic Press: Cambridge, MA, USA, 2024; pp. 387–406. [Google Scholar] [CrossRef]
- Crawford, M.B. The World beyond Your Head: On Becoming an Individual in an Age of Distraction; Farrar, Straus and Giroux: New York, NY, USA, 2015. [Google Scholar]
- Du, N.; Dai, H.; Trivedi, R.; Upadhyay, U.; Gomez-Rodriguez, M.; Song, L. Recurrent marked temporal point processes: Embedding event history to vector. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016; pp. 1555–1564. [Google Scholar]
- Saha, A.; Samanta, B.; Ganguly, N.; De, A. Crpp: Competing recurrent point process for modeling visibility dynamics in information diffusion. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management, Torino, Italy, 22–26 October 2018; pp. 537–546. [Google Scholar]
- Zuo, S.; Liu, T.; Zhao, T.; Zha, H. Differentially Private Estimation of Hawkes Process. arXiv 2022, arXiv:2209.07303. [Google Scholar]
- Hawkes, A.G. Spectra of some self-exciting and mutually exciting point processes. Biometrika 1971, 58, 83–90. [Google Scholar] [CrossRef]
- Liniger, T.J. Multivariate Hawkes Processes. Ph.D. Thesis, ETH Zurich, Zürich, Switzerland, 2009. [Google Scholar]
- Ananthanarayana, T.; Srivastava, P.; Chintha, A.; Santha, A.; Landy, B.; Panaro, J.; Webster, A.; Kotecha, N.; Sah, S.; Sarchet, T.; et al. Deep learning methods for sign language translation. ACM Trans. Access. Comput. (TACCESS) 2021, 14, 22. [Google Scholar] [CrossRef]
- Escolano, C.; Costa-jussà, M.R.; Fonollosa, J.A. Multilingual machine translation: Deep analysis of language-specific encoder-decoders. J. Artif. Intell. Res. 2022, 73, 1535–1552. [Google Scholar] [CrossRef]
- Zhou, G.; Liu, Y.; Liu, F.; Zeng, D.; Zhao, J. Improving question retrieval in community question answering using world knowledge. In Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence, Beijing, China, 3–9 August 2013. [Google Scholar]
- Zhou, G.; He, T.; Zhao, J.; Hu, P. Learning continuous word embedding with metadata for question retrieval in community question answering. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Beijing, China, 26–31 July 2015; pp. 250–259. [Google Scholar]
- Qiu, X.; Huang, X. Convolutional neural tensor network architecture for community-based question answering. In Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, Buenos Aires, Argentina, 25–31 July 2015. [Google Scholar]
- Wu, W.; Xu, S.; Houfeng, W. Question condensing networks for answer selection in community question answering. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Melbourne, Australia, 15–20 July 2018; pp. 1746–1755. [Google Scholar]
- Zhou, X.; Hu, B.; Chen, Q.; Wang, X. Recurrent convolutional neural network for answer selection in community question answering. Neurocomputing 2018, 274, 8–18. [Google Scholar] [CrossRef]
- Li, B.; Jin, T.; Lyu, M.R.; King, I.; Mak, B. Analyzing and predicting question quality in community question answering services. In Proceedings of the 21st International Conference on World Wide Web, Lyon, France, 16–20 April 2012; pp. 775–782. [Google Scholar]
- Baltadzhieva, A.; Chrupała, G. Question quality in community question answering forums: A survey. ACM Sigkdd Explor. Newsl. 2015, 17, 8–13. [Google Scholar] [CrossRef]
- Zhao, Z.; Yang, Q.; Cai, D.; He, X.; Zhuang, Y. Expert Finding for Community-Based Question Answering via Ranking Metric Network Learning. In Proceedings of the IJCAI, New York, NY, USA, 9–16 July 2016; Volume 16, pp. 3000–3006. [Google Scholar]
- Geerthik, S.; Gandhi, K.R.; Venkatraman, S. Domain expert ranking for finding domain authoritative users on community question answering sites. In Proceedings of the 2016 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), Chennai, India, 15–17 December 2016; pp. 1–5. [Google Scholar]
- Liska, A.; Kocisky, T.; Gribovskaya, E.; Terzi, T.; Sezener, E.; Agrawal, D.; Cyprien De Masson, D.; Scholtes, T.; Zaheer, M.; Young, S.; et al. Streamingqa: A benchmark for adaptation to new knowledge over time in question answering models. In Proceedings of the International Conference on Machine Learning, Baltimore, MD, USA, 25–27 July 2022; pp. 13604–13622. [Google Scholar]
- Zhuang, Y.; Yu, Y.; Wang, K.; Sun, H.; Zhang, C. Toolqa: A dataset for llm question answering with external tools. Adv. Neural Inf. Process. Syst. 2024, 36, 50117–50143. [Google Scholar]
- Quan, X.; Lu, Y.; Liu, W. Towards modeling question popularity in community question answering. In Proceedings of the 2012 IEEE 11th International Conference on Cognitive Informatics and Cognitive Computing, Kyoto, Japan, 22–24 August 2012; pp. 109–114. [Google Scholar]
- Guo, N.; Liu, C.; Li, C.; Zeng, Q.; Ouyang, C.; Liu, Q.; Lu, X. Explainable and Effective Process Remaining Time Prediction Using Feature-Informed Cascade Prediction Model. IEEE Trans. Serv. Comput. 2024, 17, 949–962. [Google Scholar] [CrossRef]
- Cheng, J.; Adamic, L.; Dow, P.A.; Kleinberg, J.M.; Leskovec, J. Can cascades be predicted? In Proceedings of the 23rd International Conference on World Wide Web, Seoul, Republic of Korea, 7–11 April 2014; pp. 925–936. [Google Scholar]
- Gupta, S.; Kambli, R.; Wagh, S.; Kazi, F. Support-vector-machine-based proactive cascade prediction in smart grid using probabilistic framework. IEEE Trans. Ind. Electron. 2014, 62, 2478–2486. [Google Scholar] [CrossRef]
- Yang, M.; Li, Z.; Zhou, M.; Liu, J.; King, I. Hicf: Hyperbolic informative collaborative filtering. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, 14–18 August 2022; pp. 2212–2221. [Google Scholar]
- Zaman, T.; Fox, E.B.; Bradlow, E.T. A bayesian approach for predicting the popularity of tweets. Ann. Appl. Stat. 2014, 8, 1583–1611. [Google Scholar] [CrossRef]
- Wu, B.; Mei, T.; Cheng, W.H.; Zhang, Y. Unfolding temporal dynamics: Predicting social media popularity using multi-scale temporal decomposition. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA, 12–17 February 2016. [Google Scholar]
- Zhong, C.; Xiong, F.; Pan, S.; Wang, L.; Xiong, X. Hierarchical attention neural network for information cascade prediction. Inf. Sci. 2023, 622, 1109–1127. [Google Scholar] [CrossRef]
- Jitkrittum, W.; Gupta, N.; Menon, A.K.; Narasimhan, H.; Rawat, A.; Kumar, S. When Does Confidence-Based Cascade Deferral Suffice? Adv. Neural Inf. Process. Syst. 2024, 36, 9891–9906. [Google Scholar]
- Bandari, R.; Asur, S.; Huberman, B.A. The pulse of news in social media: Forecasting popularity. In Proceedings of the Sixth International AAAI Conference on Weblogs and Social Media, Dublin, Ireland, 4–7 June 2012. [Google Scholar]
- Cox, D.R.; Isham, V. Point Processes; CRC Press: Boca Raton, FL, USA, 1980; Volume 12. [Google Scholar]
- Ogata, Y. Seismicity analysis through point-process modeling: A review. In Seismicity Patterns, Their Statistical Significance and Physical Meaning; Springer: Berlin/Heidelberg, Germany, 1999; pp. 471–507. [Google Scholar]
- Bray, A.; Schoenberg, F.P. Assessment of point process models for earthquake forecasting. Stat. Sci. 2013, 510–520. [Google Scholar] [CrossRef]
- Pratiwi, H.; Rini, L.S.; Mangku, I.W. Marked point process for modelling seismic activity (case study in Sumatra and Java). J. Phys. Conf. Ser. 2018, 1022, 012004. [Google Scholar] [CrossRef]
- Soriano-Redondo, A.; Jones-Todd, C.M.; Bearhop, S.; Hilton, G.M.; Lock, L.; Stanbury, A.; Votier, S.C.; Illian, J.B. Understanding species distribution in dynamic populations: A new approach using spatio-temporal point process models. Ecography 2019, 42, 1092–1102. [Google Scholar] [CrossRef]
- Bauwens, L.; Hautsch, N. Modelling financial high frequency data using point processes. In Handbook of Financial Time Series; Springer: Berlin/Heidelberg, Germany, 2009; pp. 953–979. [Google Scholar]
- Filimonov, V.; Sornette, D. Apparent criticality and calibration issues in the Hawkes self-excited point process model: Application to high-frequency financial data. Quant. Financ. 2015, 15, 1293–1314. [Google Scholar] [CrossRef]
- Zhao, Q.; Erdogdu, M.A.; He, H.Y.; Rajaraman, A.; Leskovec, J. Seismic: A self-exciting point process model for predicting tweet popularity. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA, 10–13 August 2015; pp. 1513–1522. [Google Scholar]
- Kobayashi, R.; Lambiotte, R. Tideh: Time-dependent hawkes process for predicting retweet dynamics. In Proceedings of the Tenth International AAAI Conference on Web and Social Media, Cologne, Germany, 17–20 May 2016. [Google Scholar]
- Kingman, J.F.C. Poisson Processes. In Encyclopedia of Biostatistics; John Wiley & Sons, Ltd.: Hoboken, NJ, USA, 2005. [Google Scholar] [CrossRef]
- Isham, V.; Westcott, M. A self-correcting point process. Stoch. Process. Their Appl. 1979, 8, 335–347. [Google Scholar] [CrossRef]
- Dheur, V.; Bosser, T.; Izbicki, R.; Taieb, S.B. Distribution-Free Conformal Joint Prediction Regions for Neural Marked Temporal Point Processes. arXiv 2024, arXiv:2401.04612. [Google Scholar] [CrossRef]
- Borrajo, M.; González-Manteiga, W.; Martínez-Miranda, M. Goodness-of-fit test for point processes first-order intensity. Comput. Stat. Data Anal. 2024, 194, 107929. [Google Scholar] [CrossRef]
- Kındap, Y.; Godsill, S. Point process simulation of generalised hyperbolic Lévy processes. Stat. Comput. 2024, 34, 33. [Google Scholar] [CrossRef]
- Hochreiter, S.; Schmidhuber, J. Long short-term memory. Neural Comput. 1997, 9, 1735–1780. [Google Scholar] [CrossRef]
- Cho, K.; Van Merriënboer, B.; Gulcehre, C.; Bahdanau, D.; Bougares, F.; Schwenk, H.; Bengio, Y. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv 2014, arXiv:1406.1078. [Google Scholar]
- Bahdanau, D.; Cho, K.; Bengio, Y. Neural machine translation by jointly learning to align and translate. arXiv 2014, arXiv:1409.0473. [Google Scholar]
- Luong, M.T.; Pham, H.; Manning, C.D. Effective approaches to attention-based neural machine translation. arXiv 2015, arXiv:1508.04025. [Google Scholar]
- Shen, X.; Yuan, S.; Sheng, H.; Du, H.; Yu, X. Auslan-Daily: Australian Sign Language translation for daily communication and news. Adv. Neural Inf. Process. Syst. 2024, 36, 80455–80469. [Google Scholar]
- Xu, K.; Ba, J.; Kiros, R.; Cho, K.; Courville, A.; Salakhudinov, R.; Zemel, R.; Bengio, Y. Show, attend and tell: Neural image caption generation with visual attention. In Proceedings of the International Conference on Machine Learning, Lille, France, 6–11 July 2015; pp. 2048–2057. [Google Scholar]
- Yu, L.; Buys, J.; Blunsom, P. Online segment to segment neural transduction. arXiv 2016, arXiv:1609.08194. [Google Scholar]
- Aharoni, R.; Goldberg, Y. Morphological inflection generation with hard monotonic attention. arXiv 2016, arXiv:1611.01487. [Google Scholar]
- Yang, Z.; Hu, Z.; Deng, Y.; Dyer, C.; Smola, A. Neural machine translation with recurrent attention modeling. arXiv 2016, arXiv:1607.05108. [Google Scholar]
- Deng, Y.; Kim, Y.; Chiu, J.; Guo, D.; Rush, A. Latent alignment and variational attention. Adv. Neural Inf. Process. Syst. 2018, 31, 9712–9724. [Google Scholar]
- Wu, S.; Shapiro, P.; Cotterell, R. Hard Non-Monotonic Attention for Character-Level Transduction. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, 31 October–4 November 2018; pp. 4425–4438. [Google Scholar]
- Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, Ł.; Polosukhin, I. Attention is all you need. Adv. Neural Inf. Process. Syst. 2017, 31, 5998–6008. [Google Scholar]
- Fazil, M.; Sah, A.K.; Abulaish, M. Deepsbd: A deep neural network model with attention mechanism for socialbot detection. IEEE Trans. Inf. Forensics Secur. 2021, 16, 4211–4223. [Google Scholar] [CrossRef]
- Mazzia, V.; Angarano, S.; Salvetti, F.; Angelini, F.; Chiaberge, M. Action Transformer: A self-attention model for short-time pose-based human action recognition. Pattern Recognit. 2022, 124, 108487. [Google Scholar] [CrossRef]
- Shaik, T.; Tao, X.; Li, L.; Xie, H.; Cai, T.; Zhu, X.; Li, Q. Framu: Attention-based machine unlearning using federated reinforcement learning. IEEE Trans. Knowl. Data Eng. 2024. [Google Scholar] [CrossRef]
- Shankar, S.; Sarawagi, S. Posterior Attention Models for Sequence to Sequence Learning. In Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA, 6–9 May 2019. [Google Scholar]
- Kempe, C.; Eriksson-Gustavsson, A.L.; Samuelsson, S. Are there any Matthew effects in literacy and cognitive development? Scand. J. Educ. Res. 2011, 55, 181–196. [Google Scholar] [CrossRef]
- Gómez-Bengoechea, G.; Jung, J. The Matthew effect: Evidence on firms’ digitalization distributional effects. Technol. Soc. 2024, 76, 102423. [Google Scholar] [CrossRef]
- Press, W.H.; Teukolsky, S.A.; Vetterling, W.T.; Flannery, B.P. Numerical Recipes 3rd Edition: The Art of Scientific Computing; Cambridge University Press: Cambridge, UK, 2007. [Google Scholar]
- Xiao, H. Bert-As-Service. 2018. Available online: https://github.com/hanxiao/bert-as-service (accessed on 20 May 2021).
- Devlin, J.; Chang, M.W.; Lee, K.; Toutanova, K. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv 2018, arXiv:1810.04805. [Google Scholar]
- Kingma, D.P.; Ba, J. Adam: A method for stochastic optimization. arXiv 2014, arXiv:1412.6980. [Google Scholar]
- Prechelt, L. Automatic early stopping using cross validation: Quantifying the criteria. Neural Netw. 1998, 11, 761–767. [Google Scholar] [CrossRef]
- Morales-Navarrete, D.; Bevilacqua, M.; Caamaño-Carrillo, C.; Castro, L.M. Modeling point referenced spatial count data: A Poisson process approach. J. Am. Stat. Assoc. 2024, 119, 664–677. [Google Scholar] [CrossRef]
- Kumar, P. Deep Hawkes process for high-frequency market making. J. Bank. Financ. Technol. 2024, 1–18. [Google Scholar] [CrossRef]
- Croft, W.B.; Metzler, D.; Strohman, T. Search Engines: Information Retrieval in Practice; Addison-Wesley Reading: Boston, MA, USA, 2010; Volume 520. [Google Scholar]
- Järvelin, K.; Kekäläinen, J. Cumulated gain-based evaluation of IR techniques. ACM Trans. Inf. Syst. (TOIS) 2002, 20, 422–446. [Google Scholar] [CrossRef]
Symbol | Description |
---|---|
a collection of cascades | |
a question-answer cascade | |
M | total number of question-answer cascades |
i | sequence number of a question-answer cascade |
k | represents the k-th answer |
the time when the k-th answer being posted | |
model’s estimate of the time of the k-th answer | |
the marker of the k-th answer | |
observed history up to the k-th answers | |
total number of answers in a question-answer cascade i | |
the number of answers up to time | |
model’s estimate of the number of answers at time | |
conditional intensity function | |
conditional probability density function | |
conditional cumulative distribution function | |
the negative logarithmic likelihood function |
Topic | #Questions | #Answers | #Comments | #Votes | Average Duration (Days) |
---|---|---|---|---|---|
Lifestyle | 529 | 133,782 | 582,868 | 7,372,546 | 1165 |
Economics | 751 | 71,871 | 278,613 | 2,809,376 | 1319 |
Sports | 539 | 58,885 | 387,740 | 3,856,046 | 1196 |
Internet | 209 | 37,985 | 132,640 | 2,950,844 | 698 |
Art | 544 | 60,455 | 270,134 | 3,559,153 | 1249 |
Read | 432 | 111,631 | 292,375 | 4,336,772 | 1177 |
Food | 194 | 62,467 | 342,557 | 3,834,906 | 1006 |
Animation | 475 | 48,005 | 152,896 | 1,870,583 | 410 |
Movie | 254 | 47,006 | 136,307 | 2,296,818 | 472 |
Game | 132 | 51,471 | 206,775 | 2,604,300 | 910 |
… | … | … | … | … | … |
Total | 8272 | 1,315,316 | 5,910,928 | 74,061,774 | 979 |
Topic | Nums | Top 10% | Top 20% | Earliest 10% | Earliest 20% |
---|---|---|---|---|---|
Lifestyle | 529 | 86.0 | 92.8 | 26.7 | 40.8 |
Economics | 751 | 79.8 | 88.3 | 33.3 | 45.2 |
Sports | 539 | 82.5 | 90.3 | 26.8 | 37.9 |
Internet | 209 | 82.5 | 90.9 | 30.2 | 44.2 |
Art | 544 | 77.1 | 86.5 | 26.5 | 40.2 |
Read | 432 | 83.1 | 90.6 | 29.5 | 41.4 |
Food | 194 | 90.5 | 95.6 | 28.0 | 42.9 |
Animation | 475 | 77.9 | 86.7 | 30.6 | 45.0 |
Movie | 254 | 82.8 | 90.8 | 33.9 | 48.5 |
Game | 132 | 79.2 | 88.9 | 30.6 | 47.0 |
… | … | … | … | … | … |
Mean | — | 82.1 | 90.1 | 29.6 | 43.3 |
Zhihu | ||
---|---|---|
Model | RMSE (Day) | (%) |
Naive | 4.90 | 39.82 |
Possion | 5.02 | 118.21 |
Hawkes | 4.83 | 398.11 |
RMTPP | 4.66 | 23.44 |
CYAN-RNN | 4.60 | 23.49 |
CYAN-RNN(cov) | 4.58 | 23.34 |
PARPP | 4.21 | 20.87 |
PARPP-CON(Top1%) | 4.17 | 16.92 |
PARPP-CON(Top5%) | 4.17 | 16.20 |
PARPP-CON(Top10%) | 4.14 | 16.01 |
PARPP-CON(Top15%) | 4.11 | 15.93 |
PARPP-CON(Top20%) | 4.16 | 15.99 |
P@ | NDCG@ | |||
---|---|---|---|---|
Model | 10 | 20 | 10 | 20 |
CYAN-RNN | 0.122 | 0.231 | 0.107 | 0.199 |
CYAN-RNN(cov) | 0.115 | 0.215 | 0.109 | 0.191 |
PARPPprior | 0.135 | 0.241 | 0.114 | 0.206 |
PARPP-CON(Top1%)prior | 0.157 | 0.262 | 0.109 | 0.196 |
PARPP-CON(Top5%)prior | 0.159 | 0.241 | 0.112 | 0.203 |
PARPP-CON(Top10%)prior | 0.159 | 0.252 | 0.113 | 0.206 |
PARPP-CON(Top15%)prior | 0.170 | 0.247 | 0.120 | 0.216 |
PARPP-CON(Top20%)prior | 0.170 | 0.239 | 0.114 | 0.208 |
PARPPpostr | 0.155 | 0.251 | 0.115 | 0.209 |
PARPP-CON(Top1%)postr | 0.156 | 0.262 | 0.110 | 0.199 |
PARPP-CON(Top5%)postr | 0.157 | 0.246 | 0.115 | 0.212 |
PARPP-CON(Top10%)postr | 0.166 | 0.268 | 0.115 | 0.210 |
PARPP-CON(Top15%)postr | 0.171 | 0.267 | 0.119 | 0.220 |
PARPP-CON(Top20%)postr | 0.170 | 0.248 | 0.113 | 0.206 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wu, Y.; Wen, Z.; Liang, S. Predicting Question Popularity for Community Question Answering. Electronics 2024, 13, 3260. https://doi.org/10.3390/electronics13163260
Wu Y, Wen Z, Liang S. Predicting Question Popularity for Community Question Answering. Electronics. 2024; 13(16):3260. https://doi.org/10.3390/electronics13163260
Chicago/Turabian StyleWu, Yuehong, Zhiwei Wen, and Shangsong Liang. 2024. "Predicting Question Popularity for Community Question Answering" Electronics 13, no. 16: 3260. https://doi.org/10.3390/electronics13163260