Visualization of Explanations in Recommender Systems. Al-Taie, M., Z. & Kadry, S. Journal of Advanced Management Science, 2(1):140-144, 2014.
Visualization of Explanations in Recommender Systems [link]Website  abstract   bibtex   
—Explanations in recommender systems have gained an increasing importance in the last few years. It was found that explanations can help increase users' acceptance of collaborative filtering recommender systems, helping them make decisions more quickly, convincing them to buy and even developing trust as a whole. They can also help in decision support and in problem solving. While the majority of research has focused on the algorithms behind recommender systems, little emphasis was put on interface which is crucial in improving user experience especially if we know that communicating reasoning to users is considered an important aspect of assessing recommender systems. The importance of this paper is that it lies in the area of controlling the recommendation process which gained little attention so far. The focus is on the visualization of explanations in recommender systems. We will learn what modalities (E.g. text, graphs, tables, and images) can better present explanations to users, through the review of a selection of papers in the literature over the last few years. The results show that explanations with simple graphs and descriptions can better present explanations (meaning that complex graphical interfaces can confuse users). The rest of this paper is organized as follows: the next section gives an introduction to explanations in recommender systems. Then, we talk about the relationship between visualization of explanations and other disciplines such as human computer interaction and decision making. We then talk about the different methods of information visualization especially those used when explanations are involved. The paper ends with conclusions and perspectives for future work.  Index Terms—recommender systems, explanations, information visualization, decision making, human computer interaction
@article{
 title = {Visualization of Explanations in Recommender Systems},
 type = {article},
 year = {2014},
 identifiers = {[object Object]},
 pages = {140-144},
 volume = {2},
 websites = {http://www.joams.com/index.php?m=content&c=index&a=show&catid=37&id=130},
 id = {561b73c7-795b-3cd9-aa3d-870983fc664a},
 created = {2018-07-26T10:34:49.507Z},
 file_attached = {false},
 profile_id = {2ed0fe69-06a2-3e8b-9bc9-5bdb197f1120},
 group_id = {e795dbfa-5576-3499-9c01-6574f19bf7aa},
 last_modified = {2018-12-14T12:16:32.118Z},
 read = {true},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Al-Taie2014},
 notes = {En el dominio de los sistemas inteligentes, una explicación tiene tres elementos: el contenido, el mecanismo de implementación y el formato de la presentación. Existen dos formatos: basado en texto y basado en multimedia.<br/>El paper se centra en la visualización de explicaciones para sistemas de recomendación. A través de la revisión de diferentes papers en la literatura, se observan diferentes modalidades: textos, grafos, tablas e imágenes. Los resultados muestran que las explicaciones con grafos simples y descripciones presentan las mejores explicaciones.<br/><br/>1.- Representación textual<br/>Es más efectiva una explicación con frases cortas para productos que claramente sean adecuados para los usuarios, mientras que una explicación más detallada es más efectiva para productos que no sean tan claramente adecuados. <br/><br/>2.- Representación gráfica<br/>Aumenta la credibilidad del sistema, así como la confianza y la satisfacción del usuario con elementos como layouts, tipografías, tamaños de fuente, colores, tablas, grafos, listas o imágenes. <br/><br/>Como conclusión: una buena interfaz de explicación está relacionada con la efectividad, satisfacción, confianza y lealtad.},
 private_publication = {false},
 abstract = {—Explanations in recommender systems have gained an increasing importance in the last few years. It was found that explanations can help increase users' acceptance of collaborative filtering recommender systems, helping them make decisions more quickly, convincing them to buy and even developing trust as a whole. They can also help in decision support and in problem solving. While the majority of research has focused on the algorithms behind recommender systems, little emphasis was put on interface which is crucial in improving user experience especially if we know that communicating reasoning to users is considered an important aspect of assessing recommender systems. The importance of this paper is that it lies in the area of controlling the recommendation process which gained little attention so far. The focus is on the visualization of explanations in recommender systems. We will learn what modalities (E.g. text, graphs, tables, and images) can better present explanations to users, through the review of a selection of papers in the literature over the last few years. The results show that explanations with simple graphs and descriptions can better present explanations (meaning that complex graphical interfaces can confuse users). The rest of this paper is organized as follows: the next section gives an introduction to explanations in recommender systems. Then, we talk about the relationship between visualization of explanations and other disciplines such as human computer interaction and decision making. We then talk about the different methods of information visualization especially those used when explanations are involved. The paper ends with conclusions and perspectives for future work.  Index Terms—recommender systems, explanations, information visualization, decision making, human computer interaction},
 bibtype = {article},
 author = {Al-Taie, Mohammed Z. and Kadry, Seifedine},
 journal = {Journal of Advanced Management Science},
 number = {1}
}

Downloads: 0