The long tail of recommender systems and how to leverage it

Park, Yoon-Joo; Tuzhilin, Alexander

doi:10.1145/1454008.1454012

Cited by 310 publications

(164 citation statements)

References 4 publications

Supporting

Mentioning

155

Contrasting

Unclassified

Order By: Relevance

“…We find from the figure that a large fraction of the items' popularity locates at the lower level, which means only a few items selected by a lot of people. The phenomenon is known as the long tail effect [26], [27]. This kind of effect is also known as the power law distribution.…”

Section: Property Of Item Popularity Distributionmentioning

confidence: 99%

Shilling Attack Detection in Recommender Systems via Selecting Patterns Analysis

Gao

Hua

et al. 2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYCollaborative filtering (CF) has been widely used in recommender systems to generate personalized recommendations. However, recommender systems using CF are vulnerable to shilling attacks, in which attackers inject fake profiles to manipulate recommendation results. Thus, shilling attacks pose a threat to the credibility of recommender systems. Previous studies mainly derive features from characteristics of item ratings in user profiles to detect attackers, but the methods suffer from low accuracy when attackers adopt new rating patterns. To overcome this drawback, we derive features from properties of item popularity in user profiles, which are determined by users' different selecting patterns. This feature extraction method is based on the prior knowledge that attackers select items to rate with man-made rules while normal users do this according to their inner preferences. Then, machine learning classification approaches are exploited to make use of these features to detect and remove attackers. Experiment results on the MovieLens dataset and Amazon review dataset show that our proposed method improves detection performance. In addition, the results justify the practical value of features derived from selecting patterns.

show abstract

Section: Property Of Item Popularity Distributionmentioning

confidence: 99%

Shilling Attack Detection in Recommender Systems via Selecting Patterns Analysis

Gao

Hua

et al. 2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…The new item problem (Park & Tuzhilin, 2008;Park & Chu, 2009) arises because the new items entered in RS do not usually have initial ratings, and therefore, they are not likely to be recommended. In turn, an item that is not recommended keeps unnoticed by a large part of the community of users, and as they are unaware of it, they do not rate it; this involves vicious circle in which a set of items of the RS are left out of the ratings/recommendations process.…”

Section: The Cold Start Problemmentioning

confidence: 99%

Incorporating group recommendations to recommender systems: Alternatives and performance

Ortega

Bobadilla

Hernando

et al. 2013

Information Processing & Management

View full text Add to dashboard Cite

Proporcionaré una formalización completa del método propuesto. Explicaré cómo obtener el conjunto de k vecinos del grupo de usuarios y mostraré cómo obtener recomendaciones usando dichos vecinos. Asimismo, incluiré un ejemplo detallando cada paso del método propuesto en un sistema de recomendación compuesto por 8 usuarios y 10 items.Las principales características del método propuesto son: (a) es más rápido (más eficiente) que las alternativas proporcionadas por otros autores, y (b) es al menos tan exacto y preciso como otras soluciones estudiadas. Para contrastar esta hipótesis realizaré varios experimentos que miden la precisión, la exactitud y el rendimiento del método. Los resultados obtenidos se compararán con los resultados de otras alternativas utilizadas en la recomendación de grupos. Los experimentos se realizarán con las bases de datos de MovieLens y Netflix. VIII IX ABSTRACTThe importance of recommender systems has grown exponentially with the advent of social networks. In this PhD thesis I will provide a wide vision about the state of the art of recommender systems. They were initially based on demographic, contentbased and collaborative filtering. Currently, these systems incorporate some social information to the recommendation process. In the future, they will use implicit, local and personal information from the Internet of Things.As we will see here, recommender systems based on collaborative filtering can be used to perform recommendations to group of users. Previous works have made this modification in different stages of the collaborative filtering algorithm: establishing the neighborhood, prediction phase and determination of recommended items. In thisPhD thesis I will provide a new method that carry out the unification process (many users to one group) in the first stage of the collaborative filtering algorithm: similarity metric computation.I will provide a full formalization of the proposed method. I will explain how to obtain the k nearest neighbors of the group of users and I will show how to get recommendations using those users. I will also include a running example of a recommender system with 8 users and 10 items detailing all the steps of the method I will present.The main highlights of the proposed method are: (a) it will be faster (more efficient) that the alternatives provided by other authors, and (b) it will be at least as precise and accurate as other studied solutions. To check this hypothesis I will conduct several experiments measuring the accuracy, the precision and the performance of my method. I will compare these results with the results generated by other methods of group recommendation. The experiments will be carried out using MovieLens and Netflix datasets. The kinds of filtering most used at the beginning of the RS (collaborative, content-based and demographic) were described in Pazzani (1999). Breese,

show abstract

“…If most of the users have provided only a small amount of ratings or if there is only a small amount of ratings per each item (also known as the long tail in the ratings distributions for items and users [28]) it is hard to train a model. This is especially true for some types of contextualized methods, like pre-filtering [12], since the number of ratings provided in a specific context is even lower than the overall number of ratings.…”

Section: Context-relevancy Detectionmentioning

confidence: 99%

Impact of the Context Relevancy on Ratings Prediction in a Movie-Recommender System

et al. 2013

View full text Add to dashboard Cite

Original scientific paperRecommender systems are a popular and a highly researched way of helping users get to their desired content in the huge amount of available data, and services online. Understanding the situation in which users consume the items was shown to improve the recommendation process. For that reason, context-aware recommender system (CARS) employs contextual information in order to enhance the user's model and to improve the recommendations. An issue that is still open is how to decide which pieces of contextual information to acquire and how to incorporate them into CARS, since using irrelevant piece of contextual information could have a negative impact on the recommendations. We propose a methodology for detecting which pieces of contextual information contribute to explaining the variance in the ratings, based on statistical testing. We also inspect the impact of the detected relevant pieces of contextual information on the ratings prediction based on the matrix-factorization algorithm. The experiment was conducted on the MovieAT database. The results showed a significant difference in the ratings prediction using the relevant and the irrelevant pieces of contextual information. We also confirmed the positive impact of the relevant, and negative impact of the irrelevant pieces of contextual information with respect to the uncontextualized model. Key words: Personalization, Recommender systems, Context-awarenessUtjecaj relevantnosti konteksta na predvi anje ocjena u sustavu za preporuke filmova. Sustavi za preporuke (eng. recommender systems) predstavljajučest i vrlo istražen način pružanja pomoći korisnicima u svrhu pronalaska željenog sadržaja u velikoj količini dostupnih podataka i usluga. Pokazalo se da uvid u situaciju u kojoj korisnici koriste sadržaj doprinosi kvaliteti preporuka. Zbog toga, konteksta svjesni sustavi za preporuke (eng. context-aware recommender systems CARS) koriste kontekstne informacije kako bi poboljšali model korisnika i time kvalitetu preporuka. Jedan od neriješenih problema je kako odlučiti koje kontekstne informacije je potrebno sakupiti i kako ih upotrijebiti u CARSu, budući da upotreba nebitnih kontekstnih informacija može imati negativan utjecaj na kvalitetu preporuka. Mi predlažemo metodologiju za otkrivanje onih kontekstih informacija koje doprinose objašnjavanju varijabilnosti ocjena za sadržaje, utemeljenu na statističkom testiranju. Tako er, istražujemo utjecaj otkrivenog bitnog konteksta na predvi anje ocjena utemeljeno na algoritmu faktorizacije matrica. Eksperiment je proveden na bazi podataka MovieAT. Rezultati su pokazali znatnu razliku u predvi anju ocjena prilikom korištenja bitnog i nebitnog konteksta. Ujedno je potvr en i pozitivan utjecaj bitnog, odnosno negativan utjecaj nebitnog konteksta, u odnosu na sustav koji ne koristi kontekst, što upućuje na važnost i kvalitetu detekcije.

show abstract

The long tail of recommender systems and how to leverage it

Cited by 310 publications

References 4 publications

Shilling Attack Detection in Recommender Systems via Selecting Patterns Analysis

Shilling Attack Detection in Recommender Systems via Selecting Patterns Analysis

Incorporating group recommendations to recommender systems: Alternatives and performance

Impact of the Context Relevancy on Ratings Prediction in a Movie-Recommender System

Contact Info

Product

Resources

About