Search Personalization
نویسنده
چکیده
Online search or information retrieval is one of the most common activities on the web. Over 18 billion searches are made each month, and search generates over $4 billion dollars in quarterly revenues. Nevertheless, a signicant portion of search sessions are not only long (consisting of repeated queries from the user), but are also unsuccessful, i.e., do not provide answers that the user was looking for. This presents challenges to search engine marketers, whose competitive edge depends on the quality of their search engine results. In this paper, we present a machine learning algorithm that improves search results through automated personalization using gradient-based ranking. We personalize results based on both short-term or “within-session” behavior, as well as long-term or “across-session” behavior of the user. We implement our algorithm on data from the premier search engine, Yandex, and show that it improves search results signicantly compared to non-personalized results.
منابع مشابه
Personalization in the design and production of multimedia in the e-learning environment
Aims: E-learning, is a phenomenon of the modern world That in the information era and the knowledgebased society has come into existence and in its short history has been expanded with considerable speed. The impact and application of the principle of personalization in the design and production of multimedia products in its electronic. Methods: This article is a review of the literature ...
متن کاملUsing Interactive Search Elements in Digital Libraries
Background and Aim: Interaction in a digital library help users locating and accessing information and also assist them in creating knowledge, better perception, problem solving and recognition of dimension of resources. This paper tries to identify and introduce the components and elements that are used in interaction between user and system in search and retrieval of information in digital li...
متن کاملDoes Personalization Benefit Everyone in the Same Way? Multilingual Search Personalization for English vs. Non-English Users
The web community is witnessing an increase in the amount of available multilingual content and the number of multilingual web users. With this variety, personalized search systems are needed to connect people with relevant content, regardless of the language in which the content is provided, and taking into consideration the user’s language capabilities and preferences. Therefore, search perso...
متن کاملNonintrusive Personalization in Interactive Information Retrieval
Information retrieval systems are critical for overcoming information overload. A major deficiency of existing retrieval systems is that they generally lack user modeling and are not adaptive to individual users; information about the actual user and search context is largely ignored. Personalization is expected to break this deficiency and significantly improve retrieval accuracy. However, the...
متن کاملWeb Usage Mining: Personalization based on User Positive and Negative Preferences
Most commercial search engines give the same results for the same query, not considering the user's interest. User profiling is a fundamental component of any personalization application. Most existing user profiling strategies are based on object that users are interested in ( positive preferences), but not the objects that users dislike ( negative preferences). This paper focuses on sear...
متن کاملWeb Usage Mining: Personalization based on User Positive and Negative Preferences
Most commercial search engines give the same results for the same query, not considering the user's interest. User profiling is a fundamental component of any personalization application. Most existing user profiling strategies are based on object that users are interested in ( positive preferences), but not the objects that users dislike ( negative preferences). This paper focuses on sear...
متن کامل