Providing justifications in recommender systems. Symeonidis, P., Nanopoulos, A., & Manolopoulos, Y. IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans, 38(6):1262-1272, 2008. abstract bibtex Recommender systems are gaining widespread acceptance in e-commerce applications to confront the ldquoinformation overloadrdquo problem. Providing justification to a recommendation gives credibility to a recommender system. Some recommender systems (Amazon.com, etc.) try to explain their recommendations, in an effort to regain customer acceptance and trust. However, their explanations are not sufficient, because they are based solely on rating or navigational data, ignoring the content data. Several systems have proposed the combination of content data with rating data to provide more accurate recommendations, but they cannot provide qualitative justifications. In this paper, we propose a novel approach that attains both accurate and justifiable recommendations. We construct a feature profile for the users to reveal their favorite features. Moreover, we group users into biclusters (i.e., groups of users which exhibit highly correlated ratings on groups of items) to exploit partial matching between the preferences of the target user and each group of users. We have evaluated the quality of our justifications with an objective metric in two real data sets (Reuters and MovieLens), showing the superiority of the proposed method over existing approaches.
@article{
title = {Providing justifications in recommender systems},
type = {article},
year = {2008},
identifiers = {[object Object]},
keywords = {Collaborative filtering (CF),Content-based filtering (CB),E-commerce,Justification,Recommender systems},
pages = {1262-1272},
volume = {38},
id = {214e6bd0-0d65-3fa1-a0ed-7f69f367348b},
created = {2018-09-05T07:44:16.555Z},
file_attached = {false},
profile_id = {2ed0fe69-06a2-3e8b-9bc9-5bdb197f1120},
group_id = {e795dbfa-5576-3499-9c01-6574f19bf7aa},
last_modified = {2018-12-14T12:16:31.204Z},
read = {true},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
citation_key = {Symeonidis2008},
notes = {Se propone un sistema de recomendación que construye un perfil para los usuarios en base a sus características favoritas y ofrece una explicación de la recomendación en base al perfil.<br/>El planteamiento consta de cuatro estados:<br/>1.- Creación de grupos de usuarios e items. Se forman grupos de usuarios en base a las puntuaciones realizadas. Cada grupo de usuarios habrá realizado puntuaciones similares. De forma equivalete, se forman grupos para los items.<br/>2.- Ponderación de características. Se determinan las características que describen al usuario objetivo y se establece un peso a cada característica.<br/>3.- Formación de vecindad. Se encuentran los k grupos más similares al usuario objetivo en función de las características en común y de los items evaluados.<br/>4.- Generación de recomendaciones y de las listas de justificaciones. Las recomendaciones se basan en la frecuencia de aparición de las características en común. El formato de la explicación es el siguiente: ‘Item X is recommended, because it contains features a,b,..., which are included in items Z, W, … that you have already rated’.},
private_publication = {false},
abstract = {Recommender systems are gaining widespread acceptance in e-commerce applications to confront the ldquoinformation overloadrdquo problem. Providing justification to a recommendation gives credibility to a recommender system. Some recommender systems (Amazon.com, etc.) try to explain their recommendations, in an effort to regain customer acceptance and trust. However, their explanations are not sufficient, because they are based solely on rating or navigational data, ignoring the content data. Several systems have proposed the combination of content data with rating data to provide more accurate recommendations, but they cannot provide qualitative justifications. In this paper, we propose a novel approach that attains both accurate and justifiable recommendations. We construct a feature profile for the users to reveal their favorite features. Moreover, we group users into biclusters (i.e., groups of users which exhibit highly correlated ratings on groups of items) to exploit partial matching between the preferences of the target user and each group of users. We have evaluated the quality of our justifications with an objective metric in two real data sets (Reuters and MovieLens), showing the superiority of the proposed method over existing approaches.},
bibtype = {article},
author = {Symeonidis, Panagiotis and Nanopoulos, Alexandros and Manolopoulos, Yannis},
journal = {IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans},
number = {6}
}
Downloads: 0
{"_id":"5QvcoqGrumoFowNeF","bibbaseid":"symeonidis-nanopoulos-manolopoulos-providingjustificationsinrecommendersystems-2008","downloads":0,"creationDate":"2018-09-05T13:52:59.150Z","title":"Providing justifications in recommender systems","author_short":["Symeonidis, P.","Nanopoulos, A.","Manolopoulos, Y."],"year":2008,"bibtype":"article","biburl":null,"bibdata":{"title":"Providing justifications in recommender systems","type":"article","year":"2008","identifiers":"[object Object]","keywords":"Collaborative filtering (CF),Content-based filtering (CB),E-commerce,Justification,Recommender systems","pages":"1262-1272","volume":"38","id":"214e6bd0-0d65-3fa1-a0ed-7f69f367348b","created":"2018-09-05T07:44:16.555Z","file_attached":false,"profile_id":"2ed0fe69-06a2-3e8b-9bc9-5bdb197f1120","group_id":"e795dbfa-5576-3499-9c01-6574f19bf7aa","last_modified":"2018-12-14T12:16:31.204Z","read":"true","starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"Symeonidis2008","notes":"Se propone un sistema de recomendación que construye un perfil para los usuarios en base a sus características favoritas y ofrece una explicación de la recomendación en base al perfil.<br/>El planteamiento consta de cuatro estados:<br/>1.- Creación de grupos de usuarios e items. Se forman grupos de usuarios en base a las puntuaciones realizadas. Cada grupo de usuarios habrá realizado puntuaciones similares. De forma equivalete, se forman grupos para los items.<br/>2.- Ponderación de características. Se determinan las características que describen al usuario objetivo y se establece un peso a cada característica.<br/>3.- Formación de vecindad. Se encuentran los k grupos más similares al usuario objetivo en función de las características en común y de los items evaluados.<br/>4.- Generación de recomendaciones y de las listas de justificaciones. Las recomendaciones se basan en la frecuencia de aparición de las características en común. El formato de la explicación es el siguiente: ‘Item X is recommended, because it contains features a,b,..., which are included in items Z, W, … that you have already rated’.","private_publication":false,"abstract":"Recommender systems are gaining widespread acceptance in e-commerce applications to confront the ldquoinformation overloadrdquo problem. Providing justification to a recommendation gives credibility to a recommender system. Some recommender systems (Amazon.com, etc.) try to explain their recommendations, in an effort to regain customer acceptance and trust. However, their explanations are not sufficient, because they are based solely on rating or navigational data, ignoring the content data. Several systems have proposed the combination of content data with rating data to provide more accurate recommendations, but they cannot provide qualitative justifications. In this paper, we propose a novel approach that attains both accurate and justifiable recommendations. We construct a feature profile for the users to reveal their favorite features. Moreover, we group users into biclusters (i.e., groups of users which exhibit highly correlated ratings on groups of items) to exploit partial matching between the preferences of the target user and each group of users. We have evaluated the quality of our justifications with an objective metric in two real data sets (Reuters and MovieLens), showing the superiority of the proposed method over existing approaches.","bibtype":"article","author":"Symeonidis, Panagiotis and Nanopoulos, Alexandros and Manolopoulos, Yannis","journal":"IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans","number":"6","bibtex":"@article{\n title = {Providing justifications in recommender systems},\n type = {article},\n year = {2008},\n identifiers = {[object Object]},\n keywords = {Collaborative filtering (CF),Content-based filtering (CB),E-commerce,Justification,Recommender systems},\n pages = {1262-1272},\n volume = {38},\n id = {214e6bd0-0d65-3fa1-a0ed-7f69f367348b},\n created = {2018-09-05T07:44:16.555Z},\n file_attached = {false},\n profile_id = {2ed0fe69-06a2-3e8b-9bc9-5bdb197f1120},\n group_id = {e795dbfa-5576-3499-9c01-6574f19bf7aa},\n last_modified = {2018-12-14T12:16:31.204Z},\n read = {true},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Symeonidis2008},\n notes = {Se propone un sistema de recomendación que construye un perfil para los usuarios en base a sus características favoritas y ofrece una explicación de la recomendación en base al perfil.<br/>El planteamiento consta de cuatro estados:<br/>1.- Creación de grupos de usuarios e items. Se forman grupos de usuarios en base a las puntuaciones realizadas. Cada grupo de usuarios habrá realizado puntuaciones similares. De forma equivalete, se forman grupos para los items.<br/>2.- Ponderación de características. Se determinan las características que describen al usuario objetivo y se establece un peso a cada característica.<br/>3.- Formación de vecindad. Se encuentran los k grupos más similares al usuario objetivo en función de las características en común y de los items evaluados.<br/>4.- Generación de recomendaciones y de las listas de justificaciones. Las recomendaciones se basan en la frecuencia de aparición de las características en común. El formato de la explicación es el siguiente: ‘Item X is recommended, because it contains features a,b,..., which are included in items Z, W, … that you have already rated’.},\n private_publication = {false},\n abstract = {Recommender systems are gaining widespread acceptance in e-commerce applications to confront the ldquoinformation overloadrdquo problem. Providing justification to a recommendation gives credibility to a recommender system. Some recommender systems (Amazon.com, etc.) try to explain their recommendations, in an effort to regain customer acceptance and trust. However, their explanations are not sufficient, because they are based solely on rating or navigational data, ignoring the content data. Several systems have proposed the combination of content data with rating data to provide more accurate recommendations, but they cannot provide qualitative justifications. In this paper, we propose a novel approach that attains both accurate and justifiable recommendations. We construct a feature profile for the users to reveal their favorite features. Moreover, we group users into biclusters (i.e., groups of users which exhibit highly correlated ratings on groups of items) to exploit partial matching between the preferences of the target user and each group of users. We have evaluated the quality of our justifications with an objective metric in two real data sets (Reuters and MovieLens), showing the superiority of the proposed method over existing approaches.},\n bibtype = {article},\n author = {Symeonidis, Panagiotis and Nanopoulos, Alexandros and Manolopoulos, Yannis},\n journal = {IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans},\n number = {6}\n}","author_short":["Symeonidis, P.","Nanopoulos, A.","Manolopoulos, Y."],"bibbaseid":"symeonidis-nanopoulos-manolopoulos-providingjustificationsinrecommendersystems-2008","role":"author","urls":{},"keyword":["Collaborative filtering (CF)","Content-based filtering (CB)","E-commerce","Justification","Recommender systems"],"downloads":0},"search_terms":["providing","justifications","recommender","systems","symeonidis","nanopoulos","manolopoulos"],"keywords":["collaborative filtering (cf)","content-based filtering (cb)","e-commerce","justification","recommender systems"],"authorIDs":[]}