Integrating tags in a semantic content-based recommender
Published 23 October 2008
Marco de Gemmis, Pasquale Lops, Giovanni Semeraro, Pierpaolo Basile
Citations157
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Whether folksonomies might be a valuable source of information about user interests is investigated and an improvement in the predictive accuracy of the tag-augmented recommender compared to the pure content-based one is shown.
Abstract
Basic content personalization consists in matching up the attributes of a user profile, in which preferences and interests are stored, with the attributes of a content object. The Web 2.0 (r)evolution and the advent of user generated content have changed the game for personalization, since the role of people has evolved from passive consumers of information to that of active contributors. One of the forms of user generated content that has drawn more attention from the research community is folksonomy, a taxonomy generated by users who collaboratively annotate and categorize resources of interests with freely chosen keywords called tags.
Keywords
Computer Science
A study of cross-validation and bootstrap for accuracy estimation and model selection
10,733 Citations1995Ron Kohavi
The results indicate that for real-word datasets similar to the authors', the best method to use for model selection is ten fold stratified cross validation even if computation power allows using more folds.
Foundations of statistical natural language processing
9,996 Citations1999Christopher D. Manning, Hinrich Schütze
ACM Computing SurveysMachine learning in automated text categorization
7,899 Citations2002Fabrizio Sebastiani
This survey discusses the main approaches to text categorization that fall within the machine learning paradigm and discusses in detail issues pertaining to three different problems, namely, document representation, classifier construction, and classifier evaluation.
ACM Transactions on Information SystemsEvaluating collaborative filtering recommender systems
5,762 Citations2004Jonathan L. Herlocker, Joseph A. Konstan +2 more
The key decisions in evaluating collaborative filtering recommender systems are reviewed: the user tasks being evaluated, the types of analysis and datasets being used, the ways in which prediction quality is measured, the evaluation of prediction attributes other than quality, and the user-based evaluation of the system as a whole.
A comparison of event models for naive bayes text classification
3,224 Citations1998Andrew McCallum, Kamal Nigam
It is found that the multi-variate Bernoulli performs well with small vocabulary sizes, but that the multinomial performs usually performs even better at larger vocabulary sizes--providing on average a 27% reduction in error over the multi -variateBernoulli model at any vocabulary size.
Machine LearningOn the Optimality of the Simple Bayesian Classifier under Zero-One Loss
3,072 Citations1997Pedro Domingos, Michael J. Pazzani
The Bayesian classifier is shown to be optimal for learning conjunctions and disjunctions, even though they violate the independence assumption, and will often outperform more powerful classifiers for common training set sizes and numbers of attributes, even if its bias is a priori much less appropriate to the domain.
IEEE Transactions on Knowledge and Data EngineeringSome Effective Techniques for Naive Bayes Text Classification
572 Citations2006Sang‐Bum Kim, Kyoung-Soo Han +2 more
Computational LinguisticsUsing corpus statistics and WordNet relations for sense identification
441 Citations1998Claudia Leacock, George A. Miller +1 more
A statistical classifier is described that combines topical context with local cues to identify a word sense and is used to disambiguate a noun, a verb, and an adjective.
IEEE Intelligent Systems and their ApplicationsText-learning and related intelligent agents: a survey
280 Citations1999Dunja Mladenić
Personal WebWatcher is described, a content-based intelligent agent that uses text-learning for user-customized Web browsing that focuses on three key criteria: what representation the particular application uses for documents, how it selects features, and what learning algorithm it uses.
User Modeling and User-Adapted InteractionAdaptive, intelligent presentation of information for the museum visitor in PEACH
190 Citations2007Oliviero Stock, Massimo Zancanaro +7 more
A novel integrated framework for museum visits is defined and evidence is found that even older users are comfortable interacting with a major component of the system, focusing on various aspects of PEACH.
User Modeling and User-Adapted InteractionA content-collaborative recommender that exploits WordNet-based user profiles for neighborhood formation
154 Citations2007Marco de Gemmis, Pasquale Lops +1 more
This work proposes a new content-collaborative hybrid recommender which computes similarities between users relying on their content-based profiles, in which user preferences are stored, instead of comparing their rating styles.
The University of Bath Online Publications Store (The University of Bath)Learning User Profiles from Tagging Data and Leveraging them for Personal(ized) Information Access
135 Citations2007Elke Michlmayr, Steve Cayzer
The Add-A-Tag algorithm for profile construction is presented which takes account of the structural and temporal nature of tagging data, and can be used to guide the user’s navigation, that is, to provide the user with personalized access to information resources.
Author Index
116 Citations2007
A new search-based method, which uses tags to recommend songs interesting to a user, yielding substantially improved results and a discussion of some future work to further improve tag-based search and recommendation in community Web sites.
Open Research Online (The Open University)Folksonomies, the semantic web, and movie recommendation
109 Citations2007Martin Szomszor, Ciro Cattuto +5 more
This paper investigates the question that folksonomy-generated movie tag-clouds can be used to construct better user profiles that reflect a user's level of interest in different kinds of movies, and therefore, provide a basis for prediction of their rating for a previously unseen movie.
Finding Communities of Practice from User Profiles Based On Folksonomies
101 Citations2006Jörg Diederich, Tereza Iofciu
This paper proposes to create user pro- files from the data available in folksonomy systems by letting users specify the most relevant objects in the system by using the tags associated with the specified objects to build the user profile.
Improved recommendation based on collaborative tagging behaviors
87 Citations2008Shiwan Zhao, Nan Du +4 more
A new collaborative filtering approach TBCF (Tag-based Collaborative Filtering) based on the semantic distance among tags assigned by different users to improve the effectiveness of neighbor selection, which has significant improvement against the traditional cosine-based recommendation method while leveraging user input not explicitly targeting the recommendation system.
A Study of User Profile Generation from Folksonomies
78 Citations2008Ching Man Au Yeung, Nicholas Gibbins +1 more
It is revealed that the majority of users possess multiple interests, and an algorithm is proposed to generate user profiles which can accurately represent these multiple interests.
Lecture notes in computer scienceTowards a Tag-Based User Model: How Can User Model Benefit from Tags?
64 Citations2007Francesca Carmagnola, Federica Cena +3 more
This paper investigates the possibility of exploiting the user tagging activity in order to infer knowledge about the user, and investigates the relation between tagging and user modeling.
Lecture notes in computer scienceInteractive User Modeling for Personalized Access to Museum Collections: The Rijksmuseum Case Study
63 Citations2007Yiwen Wang, Lora Aroyo +2 more
An approach for personalized access to museum collections using a RDF/OWL specification of the Rijksmuseum Amsterdam collections as a driver for an interactive dialog and the elicited user model is used for generating recommendations of artefacts and topics.
Combining learning and word sense disambiguation for intelligent user profiling
58 Citations2007Giovanni Semeraro, Marco de Gemmis +2 more
The conclusion is that the integration of linguistic knowledge in the learning process improves the classification of those documents whose classification score is close to the likes/dislikes threshold (the items for which the classification is highly uncertain).
CINECA IRIS Institutional Research Information System (University of Bari Aldo Moro)META - MultilanguagE Text Analyzer
17 Citations2008Pierpaolo Basile, Marco de Gemmis +3 more
META (MultilanguagE Text Analyzer), a tool for text analysis, designed with the aim of providing a general framework for NLP tasks over different languages, implements both basic and advanced NLP functionalities, such as Word Sense Disambiguation.