Search results for "suosittelu"
showing 10 items of 38 documents
How does serendipity affect diversity in recommender systems? A serendipity-oriented greedy algorithm
2018
Most recommender systems suggest items that are popular among all users and similar to items a user usually consumes. As a result, the user receives recommendations that she/he is already familiar with or would find anyway, leading to low satisfaction. To overcome this problem, a recommender system should suggest novel, relevant and unexpected i.e., serendipitous items. In this paper, we propose a serendipity-oriented, reranking algorithm called a serendipity-oriented greedy (SOG) algorithm, which improves serendipity of recommendations through feature diversification and helps overcome the overspecialization problem. To evaluate our algorithm, we employed the only publicly available datase…
Watch This! The Influence of Recommender Systems and Social Factors on the Content Choices of Streaming Video on Demand Consumers
2021
Streaming Video-on-demand (SVOD) services are getting increasingly popular. Current research, however, lacks knowledge about consumers’ content decision processes and their respective influencing factors. Thus, the work reported on in this paper explores socio-technical interrelations of factors impacting content choices in SVOD, examining the social factors WOM, eWOM and peer mediation, as well as the technological influence of recommender systems. A research model based on the Theory of Reasoned Action and the Technology Acceptance Model was created and tested by an n = 186 study sample. Results show that the quality of a recommender system and not the social mapping functionality is the …
Listwise Recommendation Approach with Non-negative Matrix Factorization
2018
Matrix factorization (MF) is one of the most effective categories of recommendation algorithms, which makes predictions based on the user-item rating matrix. Nowadays many studies reveal that the ultimate goal of recommendations is to predict correct rankings of these unrated items. However, most of the pioneering efforts on ranking-oriented MF predict users’ item ranking based on the original rating matrix, which fails to explicitly present users’ preference ranking on items and thus might result in some accuracy loss. In this paper, we formulate a novel listwise user-ranking probability prediction problem for recommendations, that aims to utilize a user-ranking probability matrix to predi…
Vectors of Pairwise Item Preferences
2019
Neural embedding has been widely applied as an effective category of vectorization methods in real-world recommender systems. However, its exploration of users’ explicit feedback on items, to create good quality user and item vectors is still limited. Existing neural embedding methods only consider the items that are accessed by the users, but neglect the scenario when a user gives high or low rating to a particular item. In this paper, we propose Pref2Vec, a method to generate vector representations of pairwise item preferences, users and items, which can be directly utilized for machine learning tasks. Specifically, Pref2Vec considers users’ pairwise item preferences as elementary units. …
CitySearcher: A City Search Engine For Interests
2017
We introduce CitySearcher, a vertical search engine that searches for cities when queried for an interest. Generally in search engines, utilization of semantics between words is favorable for performance improvement. Even though ambiguous query words have multiple semantic meanings, search engines can return diversified results to satisfy different users' information needs. But for CitySearcher, mismatched semantic relationships can lead to extremely unsatisfactory results. For example, the city Sale would incorrectly rank high for the interest shopping because of semantic interpretations of the words. Thus in our system, the main challenge is to eliminate the mismatched semantic relationsh…
Improving Serendipity and Accuracy in Cross-Domain Recommender Systems
2017
Cross-domain recommender systems use information from source domains to improve recommendations in a target domain, where the term domain refers to a set of items that share attributes and/or user ratings. Most works on this topic focus on accuracy but disregard other properties of recommender systems. In this paper, we attempt to improve serendipity and accuracy in the target domain with datasets from source domains. Due to the lack of publicly available datasets, we collect datasets from two domains related to music, involving user ratings and item attributes. We then conduct experiments using collaborative filtering and content-based filtering approaches for the purpose of validation. Ac…
Designing Recommendation or Suggestion Systems: looking to the future
2021
A Recommendation or Suggestion System (RSS) helps on-demand digital content and social media platforms identify associations amongst large amounts of transaction data, which are then used to provide personalised viewing and shopping recommendations to consumers. This preface introduces how RSSs are used in the marketplace and various purposes it serves. This paper is a contribution to the ongoing research beyond content-based recommender system. It presents an examination of how the Collective Intelligence Social Tagging System makes a fundamental difference to content-based recommender systems and a suggested hybrid approach to RSS architecture which uses crowdsourcing and tagging to incre…
Anthropomorphism and social presence in Human–Virtual service assistant interactions: The role of dialog length and attitudes
2022
In this study, we delve into the perceived quality of recommendations provided by AI-based virtual service assistants (VSAs). Specifically, the role of the social presence of VSAs in influencing recommendation perceptions is investigated. We also explore how the social presence of a VSA is formed and how perceived anthropomorphism plays a vital role in shaping social presence and eventually instilling trust in VSAs among consumers. These relationships are examined in the context of online government services. The results indicate that consumer interaction with VSAs - manifesting via perceived anthropomorphism, social presence, dialog length, and attitudes - improves recommendation quality p…
Comparing ranking-based collaborative filtering algorithms to a rating-based alternative in recommender systems context
2017
Suuri sisältövalikoima eri internet palveluissa, kuten verkkokaupoissa, voi aiheuttaa liian suurta informaatiomäärää, mikä heikentää asiakaskokemusta. Suosittelujärjestelmät ovat teknologioita, jotka tukevat asiakkaan päätöksentekoa tarjoamalla ennustettuja suosituksia. On yleistä, että asiakkaalle näytetään lista tuotteista, joista asiakas voisi pitää, esimerkiksi top-10 lista elokuvista. Perinteisesti nämä listat ovat tuotettu käyttäen perinteistä arvosanapohjaista menetelmää, missä tuntemattomille tuotteille ennustetaan arvosana ja järjestetty lista muodostetaan arvosanojen perusteella. Sijoitusperusteinen lähestyminen laskee käyttäjien väliset samankaltaisuudet ja ennustaa järjestetyn l…
Trusted educational networks for the internationalization of open educational resources
2013
Global educational programs have become increasingly important in Higher Education and the training sector. One promising means of global collaboration is the use of Open Educational Resources (OERs). However, this opportunity has been slow to catch on, even though millions of learning objects are freely available around the world. This paper discusses key barriers to the use of OERs, and gives recommendations for better use of materials in international collaborations. A special focus is on the development of Trusted Educational Networks, and their use within recommendation mechanisms to enhance sharing in communities of trusted colleagues. peerReviewed