资源预览内容
第1页 / 共9页
第2页 / 共9页
第3页 / 共9页
第4页 / 共9页
第5页 / 共9页
第6页 / 共9页
第7页 / 共9页
第8页 / 共9页
第9页 / 共9页
亲,该文档总共9页全部预览完了,如果喜欢就下载吧!
资源描述
Detecting Online Commercial Intention (OCI) Honghua (Kathy) Dai Microsoft Corporation One Microsoft Way, Redmond, WA 98052, USA kathydaimicrosoft.comLingzhi Zhao Tsinghua University Beijing, China zhaolz03mails.tsinghua.edu.cnZaiqing Nie Microsoft Research Asia Beijing, China zniemicrosoft.com Ji-Rong Wen Microsoft Research Asia Beijing, China jrwenmicrosoft.comLee Wang leew2khotmail.comYing Li Microsoft Corporation One Microsoft Way Redmond, WA 98052, USA yinglimicrosoft.comABSTRACT Understanding goals and preferences behind a users online activities can greatly help information providers, such as search engine and E-Commerce web sites, to personalize contents and thus improve user satisfaction. Understanding a users intention could also provide other business advantages to information providers. For example, information providers can decide whether to display commercial content based on users intent to purchase. Previous work on Web search defines three major types of user search goals for search queries: navigational, informational and transactional or resource 17. In this paper, we focus our attention on capturing commercial intention from search queries and Web pages, i.e., when a user submits the query or browse a Web page, whether he / she is about to commit or in the middle of a commercial activity, such as purchase, auction, selling, paid service, etc. We call the commercial intentions behind a users online activities as OCI (Online Commercial Intention). We also propose the notion of “Commercial Activity Phase” (CAP), which identifies in which phase a user is in his/her commercial activities: Research or Commit. We present the framework of building machine learning models to learn OCI based on any Web page content. Based on that framework, we build models to detect OCI from search queries and Web pages. We train machine learning models from two types of data sources for a given search query: content of algorithmic search result page(s) and contents of top sites returned by a search engine. Our experiments show that the model based on the first data source achieved better performance. We also discover that frequent queries are more likely to have commercial intention. Finally we propose our future work in learning richer commercial intention behind users online activities. Categories and Subject Descriptors I.6.5 MODELS AND PRINCIPLES: Model Development Modeling methodologies. General Terms Management, Measurement, Performance, Design, Experimentation, Human Factors. Keywords Intention, Search Intention, Online Commercial Intention, OCI, SVM. 1. INTRODUCTION There are two major online user activities on the Web. The first type of user activities is the well-studied browsing activity, i.e., how user visits Web pages on one or more Web sites. The second type, searching activity, is under great attention recently. Since the past decade, people started to study the phenomenon of search engines, their impact and user search behavior by surveying, statistical log analysis, and search presentation study 13678. A comprehensive review on Web searching studies can be found in 13. Recently there has been more and more work being done in the field of understanding goals and intention of search users. Understanding goals and preferences behind users search activities can help different types of information providers (e.g., search engines, E-Commerce sites, and online advertising businesses), to personalize search results and thus improve user satisfaction. Pilot research and applications can be found in 1110212 and 14 . In 1 and 7, users search intention / goals were classified into three general categories: Navigational, Informational and Transactional or Resource. The goal of a navigational query is to reach a particular web site; the intent of an informational query is to acquire information on web pages; and a user who inputs transactional queries are to perform some “web-mediated” activity. User search goals can also be represented using topical categories (189 and 22) or location attributes 21. A few efforts have been invested in automatically identify user search goals 4102021. Often times, information providers would like to know whether a user has intention to purchase or participate in commercial services, which we call “Online Commercial Intention” or OCI. Online Commercial Intention has broader scope than general search intention discussed in 1 and 7. First of all, OCI can be applied on both searching and browsing activities. Secondly, OCI of a search user can be seen as another independent dimension of search intention besides the three categories: Navigational, Informational and Transactional / Resource. Table 1 shows that Online Commercial Intention (OCI) can cover all three of the Copyright is held by the World Wide Web Conference Committee (IW
网站客服QQ:2055934822
金锄头文库版权所有
经营许可证:蜀ICP备13022795号 | 川公网安备 51140202000112号