Implicit interest indicators

Abstract

Recommender systems provide personalized suggestions about items that users will nd interesting. Typically, recommender systems require a user interface that can \intelli-gently" determine the interest of a user and use this information to make suggestions. The common solution, \ex-plicit ratings", where users tell the system what they think about a piece of information, is well-understood and fairly precise. However, having to stop to enter explicit ratings can alter normal patterns of browsing and reading. A more \intelligent" method is to use implicit ratings, where a rating is obtained by a method other than obtaining it directly from the user. These implicit interest indicators have o bvious advantages, including removing the cost of the user rating, and that every user interaction with the system can contribute to an implicit rating.Current recommender systems mostly do not use implicit ratings, nor is the ability of implicit ratings to predict actual user interest well-understood. This research studies the correlation between various implicit ratings and the explicit rating for a single Web page. A Web browser was developed to record the user's actions (implicit ratings) and the explicit rating of a page. Actions included mouse clicks, mouse movement, scrolling and elapsed time. This browser was used by o ver 80 people that browsed more than 2500 Web pages.Using the data collected by the browser, the individual implicit ratings and some combinations of implicit ratings were analyzed and compared with the explicit rating. We found that the time spent on a page, the amount of scrolling on a page and the combination of time and scrolling had a strong correlation with explicit interest, while individual scrolling methods and mouse-clicks were ine ective in predicting explicit interest.

The Impact of Modes of Mediation on the Web Retrieval Process

“…Therefore adding the support of Chapter 6: Evaluation 159 recording clicking can be a way of further improving the implicit profile generation (Rastegari and Shamsuddin 2010). The explicit profile generation can also be improved with features like the explicit rating of documents, as it was done by Claypool, Waseda and Brown (2001) who has also added the possibility of implicitly predicting the explicit rating for documents that were not rated by the user.…”

“…Implicit generation requires observing user behaviour and capturing their search histories (Shen, Tan andZhai 2006, Gasparetti andMicarelli 2007). User actions that needs to be observed includes time spent on reading a web page, saving, printing, clicking, selecting, and bookmarking (Claypool, Waseda and Brown 2001). Aoidh, Bertolotto and Wilson (2007) proposed an implicit profiling that involves capturing user mouse movements as well -e.g.…”

Language Models of Collaborative Filtering

“…User profiles can be explicitly obtained by asking users to rate items that they know. However these explicit ratings are hard to gather in a real system [5]. It is highly desirable to infer user preferences from implicit observations of user interactions with a system.…”

Personalized Search on the World Wide Web

“…Personalized systems can collect usage data on the server-side, e.g., server access logs or query and browsing histories, and/or on the client-side, such as cookies and mouse/keyboard tracking. For a closer examination on implicit feedback techniques see for example [40,17,13] and Chapter 21 of this book [43] for the related privacy concerns.…”