Towards Explaining Latent Factors with Topic Models in Collaborative Recommender Systems
Published 1 August 2013
Marco Rossetti, Fabio Stella, Markus Zanker
Citations44
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
This paper exploits Topic Models applied to textual data associated with items to find explanations for latent factors and develops a reference dataset for evaluating different strategies towards more interpretable and portable latent factor models.
Abstract
Latent factor models have been proved to be the state of the art for the Collaborative Filtering approach in a Recommender System. However, latent factors obtained with mathematical methods applied to the user-item matrix can be hardly interpreted by humans. In this paper we exploit Topic Models applied to textual data associated with items to find explanations for latent factors. Based on the Movie Lens dataset and textual data about movies collected from Freebase we run a user study with over hundred participants to develop a reference dataset for evaluating different strategies towards more interpretable and portable latent factor models.
Keywords
Computer Science
Journal of Machine Learning ResearchLatent dirichlet allocation
27,049 Citations2003David M. Blei, Andrew Y. Ng +1 more
IEEE Transactions on Knowledge and Data EngineeringToward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions
10,115 Citations2005Gediminas Adomavičius, Alexander Tuzhilin
This paper presents an overview of the field of recommender systems and describes the current generation of recommendation methods that are usually classified into the following three main categories: content-based, collaborative, and hybrid recommendation approaches.
EnvironmetricsPositive matrix factorization: A non‐negative factor model with optimal utilization of error estimates of data values
6,302 Citations1994Pentti Paatero, Unto Tapper
The relationship between Precision-Recall and ROC curves
6,255 Citations2006Jesse Davis, Mark Goadrich
It is shown that a deep connection exists between ROC space and PR space, such that a curve dominates in R OC space if and only if it dominates in PR space.
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.
Communications of the ACMProbabilistic topic models
5,549 Citations2012David M. Blei
Surveying a suite of algorithms that offer a solution to managing large document archives suggests they are well-suited to handle large amounts of data.
Recommender Systems Handbook
3,746 Citations2010Francesco Ricci⋆, Kantor, Paul B +2 more
This handbook illustrates how recommender systems can support the user in decision-making, planning and purchasing processes, and works for well known corporations such as Amazon, Google, Microsoft and AT&T.
Collaborative Filtering for Implicit Feedback Datasets
3,167 Citations2008Yifan Hu, Yehuda Koren +1 more
This work identifies unique properties of implicit feedback datasets and proposes treating the data as indication of positive and negative preference associated with vastly varying confidence levels, which leads to a factor model which is especially tailored for implicit feedback recommenders.
Reading Tea Leaves: How Humans Interpret Topic Models
1,874 Citations2009Jonathan Chang, Sean Gerrish +3 more
New quantitative methods for measuring semantic meaning in inferred topics are presented, showing that they capture aspects of the model that are undetected by previous measures of model quality based on held-out likelihood.
Recommender Systems: An Introduction
1,113 Citations2010Dietmar Jannach, Markus Zanker +2 more
Cambridge University Press eBooksRecommender Systems
844 Citations2010Dietmar Jannach, Markus Zanker +2 more
Advances in Collaborative Filtering
754 Citations2010Yehuda Koren, Robert Bell
IEEE Transactions on Information TheoryComparing Measures of Sparsity
753 Citations2009Niall Hurley, Scott Rickard
Several commonly-used sparsity measures are compared based on whether or not they satisfy these six propositions and only two of these measures satisfy all six: the pq-mean with p les 1, q > 1 and the Gini index.
Lecture notes in computer scienceOn Finding the Natural Number of Topics with Latent Dirichlet Allocation: Some Observations
711 Citations2010R. Arun, V. Suresh +2 more
A measure to identify the correct number of topics in mechanisms like Latent Dirichlet Allocation and offer empirical evidence in its favor in terms of classification accuracy and the number of Topics that are naturally present in the corpus is proposed.
Mind the gaps
147 Citations2009Rong Pan, Martin Scholz
This paper proposes two novel algorithms for large-scale OCCF that allow to weight the unknowns: Low-rank matrix approximation, probabilistic latent semantic analysis, and maximum-margin matrix factorization.
AI MagazineA Taxonomy for Generating Explanations in Recommender Systems
147 Citations2011Gerhard Friedrich, Markus Zanker
A taxonomy is proposed to categorize and review the research in the area of explanations, providing a unified view on the different recommendation paradigms, allowing similarities and differences to be clearly identified.
Lecture notes in business information processingContext-Based Service Recommendation for Assisting Business Process Design
94 Citations2011Ngoc Chan Nguyen, Walid Gaaloul +1 more
An approach that helps the business process designers facilitate the design step by providing them a list of related services to the current designed model and recommend the services whose composition context in existing designed service compositions best match the given fragment context is proposed.
One-Class Matrix Completion with Low-Density Factorizations
89 Citations2010Vikas Sindhwani, Serhat S. Bucak +2 more
This paper proposes an approach to explicitly deal with ambiguity in the customer-product matrix by treating the unobserved entries as optimization variables, similar to how Transductive SVMs implement the low-density separation principle for semi-supervised learning.
Lecture notes in business information processingRecommender Systems in Computer Science and Information Systems – A Landscape of Research
89 Citations2012Dietmar Jannach, Markus Zanker +2 more
A state-of-the-art review on recommender systems is provided, future research opportunities for recommender Systems in both computer science and information system community are proposed, and how the research avenues of both communities might partly converge are indicated.
ConstraintsPreference reasoning with soft constraints in constraint-based recommender systems
45 Citations2010Markus Zanker, Markus Jessenitschnig +1 more
This article formalizes the different variants of a constraint-based recommendation problem based on consistency and the empirical part compares the performance of different constraint- based recommendation mechanisms in offline experiments on historical data.
NeurocomputingTopic model validation
42 Citations2011Eduardo H. Ramírez, Ramón Brena +2 more
The Fowlkes-Mallows index, a known clustering validation metric, is generalized for the case of overlapping partitions and multi-labeled collections, thus making it suitable for validating topic modeling algorithms.
Information Technology & TourismConstraint-Based Recommendation in Tourism: A Multiperspective Case Study
37 Citations2009Dietmar Jannach, Markus Zanker +1 more
The findings show that constraint-based RS not only help positively influence tourist behavior, but such systems can be built cost-effectively when using appropriate knowledge acquisition and maintenance tools.