近年來，智慧型手機變得愈來愈普及，而且使用者對於智慧型手機的依賴度也愈來愈高。根據研究，手機APP的使用量較前一年成長了76%，APP漸漸成為大家解決生活上大小事中不可或缺的工具。當使用者開始有了使用APP的需求，就會去搜尋引擎搜尋他要的APP。然而傳統搜尋引擎如Google Play對於輸入的查詢往往只視為一個簡單任務來進行處理，使用者所下的搜尋詞時常是由複雜任務所驅動，常常導致搜尋結果不如預期或是需要進行一系列的查詢。
　　在本論文中，我們以複雜任務為基礎，檢索任務目標，幫助使用者尋找提供目標服務的APP與位置實體。我們的模型包含三個步驟，分別為產生任務目標，辨識手機能完成的子任務，以及對每一個複雜任務的子任務利用使用者評論找出適合的服務。本結構可以找出包含子任務的手機APP，對於部分手機無法完成的子任務，推薦適合的位置實體，進而增進使用者搜尋複雜任務的效率。

In recent years, smartphones have become more and more popular. Users thus heavily rely on smartphones to get various information. According to the research in 2014, apps usage grew 76% than previous year. Apps have become an indispensable tool day by day. Conventional search engines such like Google Play usually consider a search query as a simple task. However, the queries are often driven by complex tasks. The results are often less than expected.
In this work, we utilize the structure of complex task query and subtask goals and help users to find apps and location entities. Our Complex-Task-based Service Recommendation Model (CTSRM) contains three stages. Generating the subtask goals from complex task query, identifying the subtasks that could do on smartphones, and recommending suitable apps and location entities based on user review opinions for every subtask. CTSRM can recommend apps including subtask goals. For those subtasks which cannot do on smartphones, we recommend location entities to assist user accomplish their complex tasks.

[1] Broder, A 2002, September. A taxonomy of web search. In ACM Special Interest Group on Information Retrieval Forum (Vol.36, No.2, pp.3-10).
[2] Rose, D. E., & Levinson D. 2004, May. Understanding user goals in web search. In Proceedings of the 13th international conference on World Wide Web (pp. 13-19).
[3] Lee, U., Liu, Z., & Cho, J. 2005, May. Automatic Identification of User Goals in Web Search. In Proceedings of the 14th international conference on World Wide Web (pp.391-400).
[4] Lucchese, C., Orlando, S., Perego, R., Silvestri, F., & Tolomei, G. 2011, February. Identifying task-based sessions in search engine query logs. In Proceedings of the fourth ACM international conference on Web search and data mining (pp. 277-286).
[5] Felid, H., & Allan, J. 2013, July. Task-Aware Query Recommendation. In Proceedings of the 36th international ACM Special Interest Group on Information Retrieval conference on Research and development in information retrieval (pp. 83-92).
[6] Jones, R., & Klinkner, K. L. 2008, October. Beyond the session timeout: automatic hierarchical segmentation of search topics in query logs. In Proceedings of the 17th ACM conference on Information and knowledge management (pp. 699-708).
[7] Yan, B. & Chen, G. 2011, June. AppJoy: Personalized Mobile Application Discovery, In Proceedings of the 9th international conference on Mobile systems, applications, and services (pp. 113-126).
[8] Karatzoglou, A., Baltrunas, L., Church, K. & Böhmer, M. 2012, October. Climbing the app wall: enabling mobile app discovery through context-aware recommendations. In Proceedings of the 21st ACM international conference on Information and knowledge management (pp. 2527-2530).
[9] Liu, B., Kong, D., Gong, N. Z., Jin, H., & Xiong, H. 2015, February. Personalized Mobile App Recommendation: Reconciling pp Functionality and User Privacy Preference. In Proceedings of the Eighth ACM International Conference on Web Search and Data Mining (pp. 315-324).
[10] Papadopoulos, S., Menemenis, F., Kompatsiaris, Y., & Bratu, B. 2009, April. “Advances in Information Retrieval”: Lexical Graphs for Improved Contextual Ad Recommendation. In 31th European Conference on Information Retrieval Research (pp. 216-227).
[11] Tsatsou, D., Menemenis, F., Kompatsiaris, I., Davis, P. C. 2009, October. A Semantic Framework for Personalized Ad Recommendation based on Advanced Textual Analysis. In Proceedings of the third ACM conference on Recommender systems (pp. 217-220).
[12] He, X., Gao, M., Kan, M., Liu, Y., & Sugiyama, K. 2014, July. Predicting the Popularity of Web 2.0 Items Based on User Comments. In Proceedings of the 37th international ACM Special Interest Group on Information Retrieval conference on Research & development in information retrieval (pp. 233-242).
[13] Wijaya, D. T., & Bressan, S. 2008, October. A Random Walk on the Red Carpet: Rating Movies with User Reviews and PageRank. In Proceedings of the 17th ACM conference on Information and knowledge management (pp. 951-960).
[14] Ott, M., Cardie, C., & Hancock, J. 2012, April. Estimating the Prevalence of Deception in Online Review Communities. In Proceedings of the 21st international conference on World Wide Web (pp. 201-210).
[15] Danescu-Niculescu-Mizil, C., Kossinets, G., Kleinberg, J., & Lee, L. 2009, April. How opinions are received by online communities: a case study on amazon.com helpfulness votes. In Proceedings of the 18th international conference on World wide web (pp. 141-150).
[16] Fayazi, A., Lee, K., Caverlee, J., & Squiccilarini, A. 2015, August. Uncovering Crowdsourced Manipulation of Online Reviews. In, Proceedings of the 38th International ACM Special Interest Group on Information Retrieval Conference on Research and Development in Information Retrieval (pp. 233-242).
[17] Jones, R., & Klinkner, K. L. 2008, October. Beyond the session timeout: automatic hierarchical segmentation of search topics in query logs. In Proceedings of the 17th ACM conference on Information and knowledge management (pp. 699-708).
[18] Guo, Q., & Agichtein, E. 2010, July. Ready to buy or just browsing?: detecting web searcher goals from interaction data. In Proceedings of the 33rd international ACM Special Interest Group on Information Retrieval conference on Research and development in information retrieval (pp. 130-137).
[19] Tsai K. Y., Generating Complex Task Names with Sub-Task Goals to Improve Web Search by Utilizing Multiple Web Resources. Master’s thesis, National Cheng Kung University, Tainan, Taiwan, R.O.C., 2013.
[20] Blei, D. M., Ng, A. Y., & Jordan, M. I. Latent Dirichlet Allocation. Journal of Machine Learning Research, 3, 993-1022, 2003.
[21] Lafferty, J., Mccallum, A., and Pereira, F. 2001. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In Proceeding of International Conference of Machine Learning (pp. 282-289).
[22] Wang, T. X., Tsai, K. Y., & Lu, W. H. Identifying Real-Life Complex Task Names with Task-Intrinsic Entities from Microblogs. Ph.D.’s thesis, National Cheng Kung University, Tainan, Taiwan, R.O.C., 2014.
[23] Cen, L., Kong, D., Jin, H, & Si, L. Mobile App Security Risk Assessment: A Crowdsourcing Ranking Approach from User Comments. In Proceedings of the 2015 Society for Industrial and Applied Mathematics International Conference on Data Mining, 658-666, 2015.
[24] Kang, I. & Kim, G. 2003, July. Query type classification for web document retrieval. In Proceedings of the 26th annual international ACM Special Interest Group on Information Retrieval conference on Research and development in information retrieval (pp. 64-71).
[25] Hu, B., Liu, B., Gong, N. Z., Kong, D. & Jin, H. 2015, October. Protecting Your Children from Inappropriate Content in Mobile Apps: An Automatic Maturity Rating Framework. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management (pp. 1111-1120).
[26] Kong, D., & Jin, H. Towards Permission Request Prediction on Mobile Apps via Structure Feature Learning. In Proceedings of the 2015 Society for Industrial and Applied Mathematics International Conference on Data Mining, 604-612, 2015.
[27] Dekel, O., Manning C. D., Singer Y., Log-Linear Models for Label Ranking. Technical Report, Hebrew University and Stanford University, 2003.
[28] Ku, K. & Chen, H. (2007). Mining Opinions from the Web: Beyond Relevance Retrieval. Journal of American Society for Information Science and Technology, Special Issue on Mining Web Resources for Enhancing Information Retrieval, 58(12), pages 1838-1850.