相較於傳統集資管道，群眾募資是一種嶄新的企業融資方式，企業可以透過網際網路作為中介向群眾或贊助者募集資金實現計畫，這種低成本且傾聽市場需求的行銷方式尤其適合小型企業或者新創公司。對於募資者而言，最關心的問題莫過於募資活動的成敗以及投資者對募資活動的潛在情感，透過評論者給予的回饋，募資者可以及時地對募資計畫進行適當的修訂以提高計畫成功的機率。在本篇研究中，我們提出了機率圖模型來解決群眾募資活動之預測問題。方法上，我們蒐集美國募資平台Kickstarter的募資活動作為分析目標，將具有時間戳記的一連串留言視為序列，透過機率圖模型揭露其背後的潛在特徵，分析募資期間的動態變化以達到預測目標，且將結果與傳統分類器及其他序列分類器比較。

Compared with traditional fund-raising channels, crowdfunding has been a novel financing way in recent years. Through the Internet, enterprises can raise enough funds from crowds or sponsors to accomplish the crowdfunding project. This low-cost and market-oriented marketing strategy is especially suitable for small businesses or startups. From the viewpoint of founders, it is crucial to realize the success or failure of the projects so that can make adequate revisions of projects in time. In this research, we propose a probabilistic graphical model to deal with the problem of predicting success or failure of the crowdfunding project, and attempt to tackle the problem by using textual information like backers’ comments of a project with temporal information from Kickstarter. The model named as Conditional Topic Random Field (CTRF) can be used to disclose latent patterns behind comments of projects and predict the success of projects. Finally, we compare the performance CTRF and other sequence classifier and traditional classifiers.

Agrawal, A., Catalini, C., & Goldfarb, A. (2014). Some simple economics of crowdfunding. Innovation Policy and the Economy, 14(1), 63-97. doi:10.1086/674021
Allen, F., Carletti, E., & Valenzuela, P. (2013). Financial intermediation, markets, and alternative financial sectors. In Handbook of the Economics of Finance (Vol. 2, pp. 759-798).
Belleflamme, P., Lambert, T., & Schwienbacher, A. (2014). Crowdfunding: Tapping the right crowd. Journal of Business Venturing, 29(5), 585-609. doi:10.1016/j.jbusvent.2013.07.003
Blei, D., & Lafferty, J. (2006). Correlated topic models. Advances in neural information processing systems, 18, 147.
Blei, D. M., & Lafferty, J. D. (2006). Dynamic topic models. Paper presented at the Proceedings of the 23rd international conference on Machine learning. doi:10.1145/1143844.1143859
Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet allocation. Journal of machine Learning research, 3(4-5), 993-1022. doi:10.1162/jmlr.2003.3.4-5.993
Cao, J. W., & Xiong, L. L. (2014). Protein Sequence Classification with Improved Extreme Learning Machine Algorithms. BioMed research international, 12. doi:10.1155/2014/103054
Cheng, Y. T., Lin, Y. F., Chiang, K. H., & Tseng, V. S. (2017). Mining Sequential Risk Patterns From Large-Scale Clinical Databases for Early Assessment of Chronic Diseases: A Case Study on Chronic Obstructive Pulmonary Disease. Ieee Journal of Biomedical and Health Informatics, 21(2), 303-311. doi:10.1109/jbhi.2017.2657802
Greenberg, M. D., Pardo, B., Hariharan, K., & Gerber, E. (2013). Crowdfunding support tools: predicting success & failure. Paper presented at the CHI'13 Extended Abstracts on Human Factors in Computing Systems. doi:10.1145/2468356.2468682
Griffiths, T. L., & Steyvers, M. (2004). Finding scientific topics. Proceedings of the National Academy of Sciences of the United States of America, 101, 5228-5235. doi:10.1073/pnas.0307752101
Hassan, M. R., & Nath, B. (2005). Stock market forecasting using hidden Markov model: a new approach. Paper presented at the Intelligent Systems Design and Applications, 2005. ISDA'05. Proceedings. 5th International Conference on.
Hsu, C. K. (2018). A Hidden Topic Model for Prediction of crowdfunding Campaigns. (Master Thesis), National Cheng Kung University, Retrieved from https://hdl.handle.net/11296/2nfg7u
Jordan, M. I., Ghahramani, Z., Jaakkola, T. S., & Saul, L. K. (1999). An introduction to variational methods for graphical models. Machine learning, 37(2), 183-233. doi:10.1023/a:1007665907178
Klinger, R., & Tomanek, K. (2007). Classical probabilistic models and conditional random fields. Germany, TU, Algorithm Engineering.
Kraus, S., Richter, C., Brem, A., Cheng, C. F., & Chang, M. L. (2016). Strategies for reward-based crowdfunding campaigns. Journal of Innovation & Knowledge, 1(1), 13-23. doi:10.1016/j.jik.2016.01.010
Lafferty, J., McCallum, A., & Pereira, F. C. (2001). Conditional random fields: Probabilistic models for segmenting and labeling sequence data. Paper presented at the ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning.
Lai, C.-Y., Lo, P.-C., & Hwang, S.-Y. (2017). Incorporating Comment Text into Success Prediction of Crowdfunding Campaigns. Paper presented at the 21st PACIFIC-ASIA CONFERENCE ON INFORMATION SYSTEMS (PACIS 2017).
Lei, Y., Yayla, A. A., & Kahai, S. (2017). Guiding the Herd: The Effect of Reference Groups in Crowdfunding Decision Making. Paper presented at the Proceedings of the 50th Hawaii International Conference on System Sciences. doi:10.24251/HICSS.2017.232
Li, H., Chen, X., Zhang, Y., & Hai, M. (2018). Prediction of Financing Goal of Crowdfunding Projects. Procedia computer science, 139, 108-113. doi:10.1016/j.procs.2018.10.225
Liu, D. C., & Nocedal, J. (1989). On the limited memory BFGS method for large scale optimization. Mathematical programming, 45(1-3), 503-528. doi:10.1007/BF01589116
Lukasik, M., Srijith, P., Vu, D., Bontcheva, K., Zubiaga, A., & Cohn, T. (2016). Hawkes processes for continuous time sequence classification: an application to rumour stance classification in twitter. Paper presented at the Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).
Manning, C., Raghavan, P., & Schütze, H. (2010). Introduction to information retrieval. Natural Language Engineering, 16(1), 100-103.
Minka, T., & Lafferty, J. (2002). Expectation-propagation for the generative aspect model. Paper presented at the Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence.
Mitra, T., & Gilbert, E. (2014). The language that gets people to give: Phrases that predict success on kickstarter. Paper presented at the Proceedings of the 17th ACM conference on Computer supported cooperative work & social computing. doi:10.1145/2531602.2531656
Mollick, E. (2014). The dynamics of crowdfunding: An exploratory study. Journal of Business Venturing, 29(1), 1-16. doi:10.1016/j.jbusvent.2013.06.005
Mrva, D., & Woodland, P. C. (2006). Unsupervised language model adaptation for mandarin broadcast conversation transcription. Paper presented at the INTERSPEECH 2006 - ICSLP, Ninth International Conference on Spoken Language Processing.
Parhankangas, A., & Renko, M. (2017). Linguistic style and crowdfunding success among social and commercial entrepreneurs. Journal of Business Venturing, 32(2), 215-236. doi:10.1016/j.jbusvent.2016.11.001
Sandberg, R., Winberg, G., Branden, C. I., Kaske, A., Ernberg, I., & Coster, J. (2001). Capturing whole-genome characteristics in short sequences using a naive Bayesian classifier. Genome research, 11(8), 1404-1409. doi:10.1101/gr.186401
Siering, M., Koch, J. A., & Deokar, A. V. (2016). Detecting Fraudulent Behavior on Crowdfunding Platforms: The Role of Linguistic and Content-Based Cues in Static and Dynamic Contexts. Journal of Management Information Systems, 33(2), 421-455. doi:10.1080/07421222.2016.1205930
Steyvers, M., & Griffiths, T. (2007). Probabilistic topic models. Handbook of latent semantic analysis, 427(7), 424-440.
Vail, D. L., Lafferty, J. D., & Veloso, M. M. (2007). Feature selection in conditional random fields for activity recognition. Paper presented at the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems. doi:10.1109/IROS.2007.4399441
Viotto da Cruz, J. (2015). Competition and regulation of crowdfunding platforms: A two-sided market approach. Communications & Strategies(99), 33-50.
Wallach, H. (2002). Efficient training of conditional random fields. Master’s thesis, University of Edinburgh,
Wang, N. X., Li, Q. X., Liang, H. G., Ye, T. F., & Ge, S. L. (2018). Understanding the importance of interaction between creators and backers in crowdfunding success. Electronic Commerce Research and Applications, 27, 106-117. doi:10.1016/j.elerap.2017.12.004
Xing, Z., Pei, J., & Keogh, E. (2010). A brief survey on sequence classification. ACM Sigkdd Explorations Newsletter, 12(1), 40-48. doi:10.1145/1882471.1882478
Yuan, H., Lau, R. Y. K., & Xu, W. (2016). The determinants of crowdfunding success: A semantic text analytics approach. Decision Support Systems, 91, 67-76. doi:10.1016/j.dss.2016.08.001
Zhang, J. J., & Liu, P. (2012). Rational Herding in Microloan Markets. Management science, 58(5), 892-912. doi:10.1287/mnsc.1110.1459
Zhou, M., Lu, B. Z., Fan, W. G., & Wang, G. A. (2018). Project description and crowdfunding success: an exploratory study. Information Systems Frontiers, 20(2), 259-274. doi:10.1007/s10796-016-9723-1
Zvilichovsky, D., Inbar, Y., & Barzilay, O. (2015). Playing both sides of the market: Success and reciprocity on crowdfunding platforms. doi:10.2139/ssrn.2304101