近年來，隨著網際網路越來越發達，網路開始成為人們生活中的一部份。由於網路所帶來的方便性，越來越多的人開始在網路上進行購物，也因此網路商店的競爭也越來越激烈。在如此競爭情況下，除了利用折扣吸引客戶，網路商店會在搜尋引擎上投放廣告以吸引群眾。然而我們發現到，當使用者在查詢熱門的搜索時，他們可能會有購買商品的需求，但搜尋引擎卻沒有提供任何相關廣告。這情況同時造成了搜索引擎與網路商店的利益損失。
在本論文中，我們找到熱門搜索背後的隱含事件，並且從隱含事件當中推測出使用者可能需要的商品，並且進行推薦。我們的Query-Event-based Hot Product Recommendation (QEHPR) 模型包含三個步驟，分別為消費事件的辨識、發掘事件需求、商品推薦。首先，我們尋找熱門搜索背後所隱含的事件，由於並非每個事件都適合進行商品推薦，因此我們接下來辨識那些事件適合進行商品推薦。在找出適合進行商品推薦的事件之後，我們從這些的事件當中找出使用者不同類型的需求。最後，根據這些需求，我們就可以推薦出使用者所需要的商品並且推薦給使用者。

In recent years, with the rapid development and increasing popularity of the Internet, the web has become part of people’s lives. Since the convenience of web, more and more people tend to make online purchases. At the same time, the competition among online stores has gradually increased. In such a competitive situation, online retailers usually offer various consumption discounts for customers to attract people to visit their online shopping malls. In addition to catching people’s eyes by offering the best price to customers, the ad service from search engines is another great way for online shopping malls to meet the people with certain needs. However, we have noticed that when a user search a hot query, they may need some products. Surprisingly, search engines may not offer any product recommendation ads. This situation causes the loss of profit to both search engines and online retailers.
In this work, we find out the hidden event behind the hot query. Then we inference the products which users might be interested in, and recommend them to users. Our Query-Event-based Hot Product Recommendation (QEHPR) model contains three stages. The model first find out the hidden event behind a hot query. Since not all events are proper in recommending products such as the event “cabinet reshuffle”, we identify events that are suitable for our model to recommend products. Second, we discover different kinds of event needs from the consumption events we have collected. Finally, we recommend products based on the event needs for the given hot query.

[1] A. Sun and M. Hu., Query-guided event detection from news and blog streams. IEEE Transactions on Systems, Man, and Cybernetics, 2011.
[2] M. Hu, A. Sun, and E.-P. Lim., Event detection with common user interests. WIDM, Napa Valley, CA, 2008.
[3] C. Wang, M. Zhang, L. Ru, and S. Ma., Automatic online news topic ranking using media focus and user attention based on aging theory. CIKM, Napa Valley, CA, 2008.
[4] Q. Zhao, T.-Y. Liu, S. S. Bhowmick, and W.-Y. Ma., Event detection from evolution of click-through data. KDD, Philadelphia, PA, 2006.
[5] A. Sun, M. Hu, and E.-P. Lim., Searching Blogs and News: A Study on Popular Queries. SIGIR, 2008.
[6] Kanhabua N, Nguyen N, Nejdl W., Learning to detect event-related queries for web search. WWW, Florence, 2015.
[7] Broder, A., A taxonomy of web search. ACM SIGIR ,2002.
[8] TDT 2004: Annotation manual, 2004.
[9] C. C. Aggarwal and K. Subbian., Event detection in social streams. SDM’12, 2012.
[10] H. Becker, M. Naaman, and L. Gravano., Beyond trending topics: Real-world event identification on twitter. ICWSM’11, 2011.
[11] J. Weng and B.-S. Lee., Event detection in twitter. ICWSM’11, 2011.
[12] N. Parikh and N. Sundaresan., Scalable and near real-time burst detection from ecommerce queries. KDD, 2008.
[13] A. Sun and M. Hu., Query-guided event detection from news and blog streams. IEEE Transactions on Systems, Man, and Cybernetics, 2011.
[14] Hofmann., Probabilistic latent semantic indexing. Proceedings of the Twenty-Second Annual International SIGIR Conference, 1999.
[15] D. Blei, A. Ng, and M. Jordan., Latent Dirichlet allocation. Journal of Machine Learning Research, 2003.
[16] Asli Celikyilmaz, Dilek Hakkani-Tur, Gokhan Tur, Ashley Fidler, and Dustin Hillard., Exploiting distance based similarity in topic models for user intent detection. IEEE Workshop, 2011.
[17] Guo, J., Cheng, X., Xu, G., and Zhu, X., Intent-aware query similarity. ACM, 2011.
[18] Keisuke Uetsuji, Hidekazu yanagimoto, and Michifumi Yoshioka., User Intent Estimation from Access Logs with Topic Model. KES, 2015.
[19] H.H.Dai, L.Z.Zhao, Z.Q.Nie, J.-R.Wen, L.Wang, Y.Li., Detecting online commercial intention. ACM International WWW Conference, 2006.
[20] J.Hu, H.-J.Zeng, H.Li, C.Niu, Z.Chen., Demographic prediction based on user's browsing behavior. ACM International WWW Conference, 2007.
[21] P. Chatterjee, D.L. Hoffman, T.P. Novak., Modeling the clickstream: implications for web-based advertising efforts. Marketing Science, 2003.
[22] H. Feng, X. Qian., Recommend social network users favorite brands. PCM, 2013.
[23] H. Feng, X. Qian., Recommendation via user's personality and social contextual. ACM CIKM, 2013.
[24] S.W. Changchien, T.C. Lu., Mining association rules procedure to support on-line recommendation by customers and products fragmentation. Expert Syst, 2001.
[25] Garcia Esparza S., O’Mahony MP., Smyth B., Effective product recommendation using the real-time web. SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence, 2010.
[26] Dong, R., Schaal, M., O’Mahony, M.P., McCarthy, K., Smyth, B., Opinionated Product Recommendation. Case-Based Reasoning Research and Development, 2013.
[27] Dong, R., Schaal, M., O’Mahony, M.P., McCarthy, K., Smyth, B., Further Experiments in Opinionated Product Recommendation. ICCBR, 2014.
[28] Wang, T. X., and Lu, W. H., Constructing Complex Search Task with Subtasks to Improve Web Search and Sponsored Search Advertising.
[29] Chen, C. C., and Lu, W. H., Discovering Consumption Needs and Recommending Proper Advertisements to Improve Complex Tasks Searching
[30] Elkan C., Log-linear models and conditional random fields, CIKM, 2008
[31] K.B. Khoo and M. Ishizuka., Emerging Topic Tracking System. Web Intelligent, 2001.
[32] K.B. Khoo and M. Ishizuka., Information Area Tracking and Changes Summarizing in WWW. WebNet, 2001.
[33] Liu, Y. G. J., Ma, G. X., The Hot Keyphrase Extraction based on TF*PDF. IEEE 10th International Conference on Trust, Security and Privacy in Computing and Communications, 2011.
[34] Khoo Khyou Bun and Mitsuru Ishizuka., Topic extraction from news archive using TF*PDF algorithm. IEEE, 2002.
[35] Ghasem Heyrani-Nobari, Tat-Seng Chua., User Intent Identification from Online Discussions Using a Joint Aspect-Action Topic Model. AAAI, 2014.
[36] Newman, David, Chemudugunta Chaitanya, Smyth Padhraic, Steyvers Mark., Analyzing entities and topics in news articles using statistical topic models. IEEE, 2006.
[37] Li, Z., Wang, B., Li, M., Ma, W., A Probabilistic Model for Retrospective News Event Detection. SIGIR, 2005.
[38] Joachims, T., Text Categorization with Support Vector Machines: Learning with Many Relevant Features. 1998.
[39] A. Basu, C. Watters, and M. Shepherd.,Support Vector Machines for Text Categorization. IEEE, 2002.
[40] Chih-Chung Chang, and Chih-Jen Lin., LIBSVM: A Library for Support Vector Machines. ACM, 2011.