改善三贏架構之行動廣告效果｜國立中央大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	吳禹欣 Yu-hsin Wu
論文名稱：	改善三贏架構之行動廣告效果 Effectiveness Improvement for Mobile Advertising in Triple-win Framework
指導教授：	張嘉惠 Chia-hui Chang
口試委員:
學位類別：	碩士 Master
系所名稱：	資訊電機學院 - 資訊工程學系 Department of Computer Science & Information Engineering
論文出版年：	2012
畢業學年度：	101
語文別：	英文
論文頁數：	77
中文關鍵詞：	行動廣告、查詢字不符、資訊檢索模型
外文關鍵詞：	query likelihood model, LDA smoothing, relevance model, vocabulary mismatch
相關次數：	點閱：11 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

隨著近年來智慧型手機的普及與行動廣告產業的快速發展，三方互利的行動廣告概念架構，使電信業者的寬頻用戶數增加，行動廣告商的顧客數目增加，且使用者能取得網路使用費的折扣或商品折價券，並且利用地點因素和傳統檢索模型做廣告配置[4]。然而，在[4]所提出的廣告配置演算法中所使用的vector space model，卻有嚴重的vocabulary mismatch問題，導致檢索效果低落。
行動廣告推薦具有文件/查詢詞很短，以及須考慮地理位置的因素，如何找到適合的檢索模型與以上兩因素結合將是關鍵的議題。因此，我們區分出對地點敏感的查詢詞及與地點無關的查詢詞，以便使廣告配置演算法能針對各式各樣的查詢詞作不同的處理。針對對地點敏感的查詢詞，如何在廣告配置演算法中，於廣告相關性和廣告距離之間做正確的取捨，將是非常關鍵的議題；針對與地點無關的查詢詞，由於短的文件和查詢詞長久以來已經是行動廣告與生俱來存在的因素，故行動廣告推薦系統仍需解決vocabulary mismatch問題。因此，在此篇研究，我們主要聚焦在利用relevance model及LDA smoothing來舒緩vocabulary mismatch的問題，以改善檢索效果。
在實驗部分，我們比較relevance model, vector space model, query likelihood model with LDA smoothing三者之間的檢索效果，針對34名受試者的平均結果顯示，我們提出利用relevance model的方法達到最好的檢索效果。
雖然relevance model有很好的檢索效果，但其計算時間卻也相當驚人。為了縮短計算時間，在預估relevance model時，我們只把PMLE(w|D)及PQL(q|D)權重值高的document包含進去，而在做KL-divergence的加總時，我們只把P(w|Q)權重值高的words包含進去，這些效率上的考量讓使用relevance model的廣告配置演算法能在短時間內完成複雜的計算。

Mobile ad recommendation features short documents/queries and location factor. How to combine these two factors with proper IR model is the key issue. Hence, we distinguish location-sensitive queries from location-independent queries such that the ad-matching algorithm could react differently for various queries. For those location-sensitive queries, it is difficult to attain excellent recommendation effectiveness with traditional retrieval model. The relevance of recommended ads under the constraint of user accessibility could not be as relevant as the relevance of recommended ads without limit of distance. Thus, to model the tradeoff between ad relevance and ad distance to the user in personalized ad-matching algorithm is a key issue. As for location-independent queries, mobile ad matching system still have to solve vocabulary mismatch problem because short documents and short queries have been the inherent part of mobile advertising. Hence, we focus on improvement of retrieval effectiveness to relieve vocabulary mismatch problem via relevance model and LDA smoothing.
We compare the retrieval effectiveness of the relevance model with vector space model and query likelihood model with LDA smoothing. The average result over 34 users showed that our proposed approach with relevance model achieved the best performance.
Although relevance model is effective in ad matching, the computation time takes long time due to complicated calculation. Thus, we consider only high-weighted PMLE(w|D) values and high-weighted PQL(q|D) values in the estimation of relevance model, and top-ranked words with high-weighted P(w|Q) value in the summation of KL-divergence. The efficiency consideration makes the complex computation of the ad matching algorithm with relevance model finished in limited time.

中文摘要    iv
Abstract    v
誌謝    vi
Table of Contents    viii
List of Figures    x
List of Tables    xi
Chapter 1    Introduction    1
Chapter 2    Related Work    6
  2.1 Mobile Advertising    6
  2.2 Retrieval Model    9
    2.2.1 Relevance Model    13
    2.2.2 Topic Model    15
Chapter 3    Design Methodology    17
  3.1    Factors for Mobile Ad Recommendation    17
  3.2    System Architecture    19
  3.3    Personalized Ad Matching Algorithm    21
  3.4    Improvement in Retrieval Effectiveness    26
    3.4.1 Query Likelihood Model with LDA Smoothing    27
    3.4.2 Relevance Model for Query Representation    29
    3.4.3 Non-relevance Model for Query Representation    31
Chapter 4    Mobile Ad Collector    33
  4.1    Ad-crawler Platform    33
  4.2    Ad Feature Extraction    34
    4.2.1 Postal Address Extraction    35
    4.2.2 Text Preprocessing    35
    4.2.3 Training Data Preparation    38
    4.2.4 Promotion Activity Identification    39
    4.2.5 Category Prediction    41
Chapter 5    Experiment    43
  5.1    Parameter Tuning for Effectiveness Consideration  43
    5.1.1 Parameter Tuning for Query Likelihood Model with LDA Smoothing    43
    5.1.2 Parameter Tuning for Relevance Model    44
    5.1.3 Parameter Tuning for Non-relevance Model    47
    5.1.4 Summary for Parameter Tuning    48
  5.2    Efficiency Consideration for Relevance Model    49
  5.3    Simulated Platform    54
  5.4    Experimental Evaluation    58
Chapter 6    Conclusion and Future Work    61
Reference    63

                                

[1]Anagnostopoulous, A., Broder, A.Z., Gabrilovich, E., Josifovski, V., & Riedei, L. (2007). Just-in-Time Contextual Advertising. In Proceedings of the 16th International Conference on Conference on Information and Knowledge Management (ACM CIKM’07) (pp. 331-340). Lisbon: ACM.
http://portal.acm.org/citation.cfm?id=1150411
[2]Blei, D. M., Ng, A. Y., and Jordan, M. J. (2003). Latent Dirichlet Allocation. In Journal of Machine Learning Research, 3, pp. 993-1022.
[3]Broder, A., Fontoura, M., Josifovski, V., & Riedel, L. (2007). A semantic approach to contextual advertising. In Proceedings of the 30th International ACM SIGIR conference on Research and Development in Information Retrieval (2007) (pp. 559-566). Amsterdam: ACM.
[4]Chang, C.H., & Huo, K.H. (2011). Mobile Advertising: Triple-win for Consumers, Advertisers and Telecom Carriers. SIGIR Workshop on Internet Advertising, Beijing, China.
[5]Chatterjee, P., Hoffman, D. L., and Novak, T. P. (2003). Modeling the Clickstream: Implications for Web-Based Advertising Efforts, Marketing Science, vol. 22, pp. 520-541.
[6]Chen, B.L., Chen, P.N., and Chen, K.Y. (2011) Query Modeling for Spoken Document Retrieval. IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp.389-394
[7]Croft, B., Metzler, M., Strohman, T. (2010). Search Engines: Information Retrieval in Practice, Pearson Education
[8]Fan, T.K., & Chang, C.H. (2009). Sentiment-Oriented Contextual Advertising. The 31st European Conference on Information Retrieval (ECIR’09), LNCS, 5478, pp. 202-215.
[9]Fan, T.K. and Chang, C.H (2011). Blogger-Centric Contextual Advertising. Journal of Expert Systems with Applications, Vol. 38, Issue. 3, pp. 1777-1788.
[10]Fan, T.K. and Chang, C.H (2010). Sentiment Oriented Contextual Advertising. Journal of Knowledge and Information System, Vol. 23, No. 3, pp. 321-344.
[11]Feng, J., Bhargava, H.K., & Pennock, D. (2003). Comparison of Allocation Rules for Paid Placement Advertising in Search Engine. In Proceedings of the 5th International conference on Electronic Commerce (ACM EC’03) (pp. 294 - 299). Pittsburgh: ACM.
[12]Kazienko, P., & Adamski, M. (2007). AdROSA-Adaptive personalization of web advertising. Information Sciences, 177(11), pp. 2269-2295.
[13]Lacerda, A., Cristo, M., Goncalves, M.A., Fan, W.g., Ziviani, N., & Ribeiro-Neto, B. (2006). Learning to advertise. In Proceedings of the 29th International Conference on Research and Development in Information Retrieval (ACM SIGIR) (pp. 549-556) Seattle.
[14]Langheinrich, M., Nakamura, A., Abe, N., Kamba, T., & Koseki, Y. (1999). Unintrusive customization techniques for Web advertising. The International Journal of Computer and Telecommunications Networking, 31(11-16), 1259-1272.
[15]Lavrenko, V. and Croft, W. B. (2001). Relevance-based language models. In Research and Development in Information Retrieval, pp. 120-127.
[16]Liu, X., & Croft, W. B. (2004). Cluster-based retrieval using language models. In the Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval, Sheffield, United Kingdom.
[17]Penev, A., Wong, R. K. (2009) Framework for Timely and Accurate Ads on Mobile Devices, CIKM Proceedings of the 18th ACM conference on Information and knowledge management, November 2–6, Hong Kong, pp. 1067-1076.
[18]Ponte, J., Croft, W. B. (1998). A language modeling approach to information retrieval. In the Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval, pp.275-281.
[19]Rao, B., Minakakis, L. (2003) "Evolution of Mobile Location-based Services," Communications of the ACM - Mobile computing opportunities and challenges, Volume 46 Issue 12, December, pp. 61-65.
[20]Ribeiro-Neto, B., Cristo, M., Golgher, P.B., & Moura, E.S.d. (2005). Impedance coupling in content-targeted advertising. In Proceedings of the 28th annual international Conference on Research and Development in Information Retrieval (ACM SIGIR) (pp. 496-503). Salvador: ACM.
[21]Wei, X., & Croft, W. B. (2006). LDA-based document models for ad-hoc retrieval. In the Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval, Seattle, Washington, USA.
[22]Xu, D. J., Liao, S. S., Li, Q. (2008). Combining empirical experimentation and modeling techniques: A design research approach for personalized mobile advertising applications, Decision Support Systems 44.
[23]Yi, X. and Allan, J., (2009) A Comparative Study of Utilizing Topic Models for Information Retrieval, Proceedings of ECIR: 31st European Conference on Information Retrieval, LNCS 5478, pp.29-41.
[24]Zhai, C. X., Lafferty, J., (2001) A Study of Smoothing Methods for Language Models Applied to Ad-Hoc Information Retrieval, In: Proceedings of ACM SIGIR, pp. 334–342
[25]Zhai, C. X. (2008) Statistical Language Models for Information Retrieval: A Critical Review, Foundations and Treands in Information Retrieval, 2(3), pp.137-213
[26]Zhang, Y., Surendran, A.C., Platt, J.C., & Narasimhan, M. (2008). Learning from multi-topic web documents for contextual advertisement. In Proceeding of the 14th International conference on Knowledge Discovery and Data mining (ACM SIGKDD’08) (pp. 1051-1059). Las Vegas: ACM.

簡易檢索 / 詳目顯示

相關論文