-
摘要: App正在移动平台与Web平台上吸引着越来越多的关注。由于当前App市场的自组织特性, app的描述书写地并不正式, 其还包含了众多噪音词和句子。因此, 对于大多数app, 它们的功能未被很好地文档化, 所以也不易于被app搜索引擎获取。本文通过识别app描述中信息最丰富词汇的方法研究了推断一个app真实功能这一问题。为了以一种适当的方式来运用和集成app语料库的多样化信息, 我们提出了一个概率主题模型来发现app语料库中隐含的数据结构。此主题模型的结果进一步可用于识别一个app的功能和其信息最丰富的词汇。我们分别在从Google Play和Windows Phone Store所爬取的真实数据集上进行大量实验, 并验证所提出方法的有效性。Abstract: Apps are attracting more and more attention from both mobile and web platforms. Due to the self-organized nature of the current app marketplaces, the descriptions of apps are not formally written and contain a lot of noisy words and sentences. Thus, for most of the apps, the functions of them are not well documented and thus cannot be captured by app search engines easily. In this paper, we study the problem of inferring the real functions of an app by identifying the most informative words in its description. In order to utilize and integrate the diverse information of the app corpus in a proper way, we propose a probabilistic topic model to discover the latent data structure of the app corpus. The outputs of the topic model are further used to identify the function of an app and its most informative words. We verify the effectiveness of the proposed methods through extensive experiments on two real app datasets crawled from Google Play and Windows Phone Store, respectively.
-
Keywords:
- app function /
- document /
- topic model
-
-
[1] Liu S, Wang S, Zhu F, Zhang J, Krishnan R. HYDRA:Large-scale social identity linkage via heterogeneous behavior modeling. In Proc. ACM SIGMOD, June 2014, pp.51-62.
[2] Tong Y, Cao C C, Chen L. TCS:Efficient topic discovery over crowd-oriented service data. In Proc. the 20th SIGKDD, August 2014, pp.861-870.
[3] Baeza-Yates R, Jiang D, Silvestri F, Harrison B. Predicting the next app that you are going to use. In Proc. the 8th WSDM, February 2015, pp.285-294.
[4] She J, Tong Y, Chen L, Cao C C. Conflict-aware eventparticipant arrangement. In Proc. the 31st ICDE, April 2015, pp.735-746.
[5] She J, Tong Y, Chen L. Utility-aware social eventparticipant planning. In Proc. ACM SIGMOD, May 31-June 4, 2015, pp.1629-1643.
[6] Tong Y, Meng R, She J. On bottleneck-aware arrangement for event-based social networks. In Proc. the 31st ICDE Workshops, April 2015, pp.216-223.
[7] Blei D M, Ng A Y, Jordan M I. Latent Dirichlet allocation. Journal of Machine Learning Research, 2003, 3:993-1022.
[8] Griffiths T L, Steyvers M. Finding scientific topics. Proc. the National Academy of Sciences, 2004, 101(Suppl.1):5228-5235.
[9] Jo Y, Oh A H. Aspect and sentiment unification model for online review analysis. In Proc. the 4th WSDM, February 2011, pp.815-824.
[10] Sato I, Nakagawa H. Topic models with power-law using Pitman-Yor process. In Proc. the 16th SIGKDD, July 2010, pp.673-682.
[11] Wang C, Wang J, Xie X, Ma W Y. Mining geographic knowledge using location aware topic model. In Proc. the 4th ACM Workshop on GIR, November 2007, pp.65-70.
[12] Yin Z, Cao L, Han J, Zhai C, Huang T. Geographical topic discovery and comparison. In Proc. the 20th WWW, March 28-April 1, 2011, pp.247-256.
[13] Jiang D, Vosecky J, Leung K W T, Ng W. G-WSTD:A framework for geographic web search topic discovery. In Proc. the 21st CIKM, October 29-November 2, 2012, pp.1143-1152.
[14] Jiang D, Leung K W T, Ng W, Li H. Beyond click graph:Topic modeling for search engine query log analysis. In Proc. the 18th DASFAA, April 2013, pp.209-223.
[15] Sizov S. Geofolk:Latent spatial semantics in Web 2.0 social media. In Proc. the 3rd WSDM, February 2010, pp.281-290.
[16] Eisenstein J, O'Connor B, Smith N A, Xing E P. A latent variable model for geographic lexical variation. In Proc. the EMNLP, October 2010, pp.1277-1287.
[17] Jiang D, Leung K W T, Vosecky J, Ng W. Personalized query suggestion with diversity awareness. In Proc. the 30th ICDE, March 31-April 4, 2014, pp.400-411.
[18] Jiang D, Leung K W T, Ng W. Query intent mining with multiple dimensions of web search data. World Wide Web, 2015.
[19] Hao Q, Cai R, Wang C, Xiao R, Yang J M, Pang Y, Zhang L. Equip tourists with knowledge mined from travelogues. In Proc. the 19th WWW, April 2010, pp.401-410.
[20] Teh Y W. A hierarchical Bayesian language model based on Pitman-Yor processes. In Proc. the 44th ACL, July 2006, pp.985-992.
[21] El-Arini K. Dirichlet Processes:A Gentle Tutorial. 2008. https://www.cs.cmu.edu/~kbe/dptutorial.pdf, Aug. 2015.
[22] Wallach H M. Structured topic models for language[Ph.D. Thesis]. Univ. Cambridge, 2008.
[23] Rosen-ZviM, Griffiths T, Steyvers M, Smyth P. The authortopic model for authors and documents. In Proc. the 20th UAI, July 2004, pp.487-494.
[24] Xia H, Li J, Tang J, Moens M F. Plink-LDA:Using link as prior information in topic modeling. In Proc. the 17th DASFAA, April 2012, pp.213-227.
计量
- 文章访问数: 49
- HTML全文浏览量: 1
- PDF下载量: 1213
下载:
