CONCLUSION & FUTURE WORK Hybrid (Statistical in addition to Knowledge-based) Multi-Application User Interest Modeling Sampath Jayarathna in addition to Frank Shipman ABSTRACT USER INTEREST MODELING

CONCLUSION & FUTURE WORK Hybrid (Statistical in addition to Knowledge-based) Multi-Application User Interest Modeling Sampath Jayarathna in addition to Frank Shipman ABSTRACT USER INTEREST MODELING www.phwiki.com

CONCLUSION & FUTURE WORK Hybrid (Statistical in addition to Knowledge-based) Multi-Application User Interest Modeling Sampath Jayarathna in addition to Frank Shipman ABSTRACT USER INTEREST MODELING

Farran, Howard, Founder and Publisher has reference to this Academic Journal, PHwiki organized this Journal CONCLUSION & FUTURE WORKNormally, users per as long as m search tasks using multiple applications in concert: a search engine interface presents lists of potentially relevant documents; a document reader displays their contents; in addition to a third tool—a text editor or personal in as long as mation management application—is used to record notes in addition to assessments (MS Word in addition to MS PowerPoint). An Interest Profile Manager infers users’ interests from their interactions with the multi-applications, coupled with the characteristics of the multi-source interest modeling techniques. The resulting interest profile is used to generate visualizations that direct users’ attention to documents or parts of documents that match their inferred interests. Statistical methods used in the work (tf-idf, LDA an LSA) infer the interest based on the content similarity in addition to the Ontology-based user model infers the long-term user interest dynamically using spreading activation module. Acknowledgements : This research is supported by NSF grant 0938074Hybrid (Statistical in addition to Knowledge-based) Multi-Application User Interest Modeling Sampath Jayarathna in addition to Frank ShipmanComputer Science & Engineering, Texas A&M University – College StationABSTRACTWe are interested about open-ended in as long as mation gathering tasks—search tasks in particular—in which people collect Web documents as long as interpretation in addition to synthesis. User interests are usually distributed in different systems during search tasks. Traditional user interest modeling methods are not designed as long as integrating in addition to analyzing interests from multiple sources, hence, they are not very effective as long as obtaining comparatively complete description of user interests in a multi-application environment.  We propose an approach of user interest modeling based on multi-source interest fusion using statistical/algebraic models (tf-idf, LSA, in addition to LDA) in addition to knowledge-based models (Ontology). Figure 1. Multi-Application Interest Modeling in addition to Fusion Even with the best search engine in addition to the most effective query as long as mulation, “search tasks” require people to work through long lists of documents to synthesize the in as long as mation they need; there is usually no single document containing one right answer. In fact, as people skim early documents, they may determine additional in as long as mation needs that suggest further queries in addition to results in even more documents to process.  A system can support document search tasks by recommending the documents that best match a user’s interests, thereby ensuring that the user’s time is spent efficiently on the most relevant documents. In the work we present, recommendations based on demonstrated user interest; in other words, the user’s previous interactions with the document collection, along with the characteristics of the documents, are used to infer the user’s interests. USER INTEREST MODELINGWebAnnotate – During in as long as mation task, useful documents may be long, in addition to cover multiple subtopics; users may read some segments in addition to ignore others. In order to record which portion(s) of the document pique the user’s interests, an explicit interest expressions (e.g. annotations using WebAnnotate) capturing tool is used . Latent Semantic Analysis (LSA) – The SVD based LSA can take a large matrix of term document association data in addition to construct a semantic space where terms in addition to documents that are closely associated can be detected with Cosine Similarity. Latent Dirichlet Allocation (LDA) – Our strategy in using LDA is to describe users as a mixture of topics in addition to to assume that each of their actions is motivated by choosing a topic of interest in addition to subsequently a word to describe that action from the catalog of words consistent with that particular interest. We represent each user as a bag of words extracted from those actions in addition to we use the search task to denote generating a word from the bag. Figure 2. Personalized Search & RecommendationsOntology-based User Model – An ontological approach to user profiling has proven to be successful in addressing the cold-start problem in recommender systems where no initial in as long as mation is available early on upon which to base recommendations. We model the user interests using ontological profiles by assigning implicitly derived interest scores to existing concepts in domain ontology. A spreading activation algorithm is used to maintain the interest scores based on the user’s ongoing behavior.Ontology = Long-term user interest modelingStatistical Methods = Short-term user interest modelingREFERENCESSEARCH AND RECOMMENDATIONSOur major contributions in this work can be summarized as: A novel personalized search & Recommendations based on evidence coming from multiple applications in addition to multi-source interest modeling using a hybrid of statistical in addition to knowledge-based methods. In the future we plan on creating a weighting schema to identify the importance of evidence coming from multiple applications like VKB, Web Browser, Word in addition to PowerPoint.Tolomei, G., Orl in addition to o, S. in addition to Silvestri, F., Towards a task-based search in addition to recommender systems. in In Proceedings of ICDE Workshops, (2010), 333-336.Bae, S., Hsieh, H., Kim, D., Marshall, C.C., Meintanis, K., Moore, J.M., Zacchi, A. in addition to Shipman, F.M. Supporting document triage via annotation-based visualizations. American Society as long as In as long as mation Science in addition to Technology, 45 (1). 1-16.L in addition to auer, T., Foltz, P.W. in addition to Laham, D. An Introduction to Latent Semantic Analysis. Discourse Processes 25. 259-284.Sieg A, Mobasher B, in addition to Burke R., “Web search personalization with ontological user profiles,” in ACM Sixteenth Conference on In as long as mation in addition to Knowledge Management, CIKM 2007, Lisbon, Portugal, November 2007.

American University US www.phwiki.com

This Particular University is Related to this Particular Journal

Farran, Howard Hygienetown Founder and Publisher www.phwiki.com

Farran, Howard Founder and Publisher

Farran, Howard is from United States and they belong to Hygienetown and they are from  Phoenix, United States got related to this Particular Journal. and Farran, Howard deal with the subjects like Dentistry

Journal Ratings by American University

This Particular Journal got reviewed and rated by American University and short form of this particular Institution is US and gave this Journal an Excellent Rating.