Personalizing search via automated analysis of interests and activities

By Jaime Teevan, Susan T. Dumais, Eric Horvitz. Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2005

905 citations recorded by the source corpus.

Subfields: Information Systems, Information Systems and Management

View Paper: https://www.semanticscholar.org/paper/21321bad706a9f9dbb502588b0bb393cf15fa052

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Information Systems and Management

Citations in the corpus

Persona-ization: Searching on Behalf of Others (2015, background): “A sampling of such work includes extracting short- and long-term topical profiles [7][5][12][10][14], using weighted termvectors based on long-term desktop activities [13], leveraging a user's location [2], and using the user's previous queries and clicks [4][3][11].”
Personalized query expansion for the web (2007, methodology): “[34] modified the query term weights from the BM25 weighting scheme to incorporate user interests as captured by their Desktop indexes; (2) In Chirita et al.”
KDD CUP-2005 report: facing a great challenge (2005, background): “Given the exponential growth of information s availability in electronic form, search becomes one of the most important and effective approaches to finding correct/relevant information to serve our needs.”
Beliefs and biases in web search (2013, background): “Beyond aggregating search behavior across all users, search engines can also cater to the individual needs of their users via personalization, presenting the opportunity to model their preferences within the current session [42][46] and across multiple sessions [34][38][45].”
Take This Personally: Pollution Attacks on Personalized Services (2013, background): “are not public, but many previous studies have explored aspects of personalized search [2,4,6,7,9,10,14–18].”
Probabilistic factor models for web site recommendation (2011, background): “in [28] also utilized implicit information about users’ interests to re-rank Web search results within a relevance feedback framework.”
A large-scale evaluation and analysis of personalized search strategies (2007, background): “Various personalization strategies including [21, 22, 26, 31, 14, 9, 35, 30, 19] have been proposed, and personalized web search systems have been developed, but they are far from optimal.”
Personalized Search (2015, background): “In order to address the issue of irrelevant ranking, personalized search has attracted much interest in both academia [16] [46] [45] [25] [43] [35] [4] [3] and in the enterprise world, for instance at Amazon [28], Netflix [2], Facebook [48], Yahoo! [38], Microsoft [42], and Google [6] [11].”
Exploring Time-Dependent Concerns about Pregnancy and Childbirth from Search Logs (2015, background): “Temporal trends can present opportunities and challenges for personalized search [4,29].”
Evaluation of contextual information retrieval effectiveness: overview of issues and research (2010, background): “…user proﬁle: 1. user behavior, seen as set of implicit feedback indicators [60] such as past click history, clickthrough data, browsing features [92,108], eye-tracking [57], 2. bookmarks as clues for predicting user preferences [38], 3. desktop information [32] and contextual information sources…”
Mining long-term search history to improve search accuracy (2006, background): “Such work includes [9], which interpolates the current query with different chunks (time periods) of history (browsed web pages) for personalized search, and [10], which constructs user profiles from indexed desktop documents for search result reranking.”
Large Language Models for Information Retrieval: A Survey (2023, neutral): “Additionally, reranking can accommodate other specific requirements, such as personalization [15–18] and diversification [19–22].”
To personalize or not to personalize: modeling queries with variation in user intent (2008, background): “Recent work on personalized search systems has focused on developing algorithms that personalize results using a representation of an individual‟s interests [3, 5, 20, 23].”
User Profiles for Personalized Information Access (2007, background): “[98] evaluated a variety of information sources available to a client-side profiling agent, i.”
Web search personalization with ontological user profiles (2007, background): “Since the users are reluctant to specify their underlying intent and search goals, personalization must pursue techniques that leverage implicit information about the user’s interests [27, 33].”
What do people ask their social networks, and why?: a survey study of status message q&a behavior (2010, background): “, [27]) cannot yet achieve the same degree of personalization as a close friend.”