Improving Content Recommendation in Social Streams via Interest Model

Author(s):  
Junjie Zhang ◽  
Yongmei Lei
Author(s):  
Susana Fernández-Lores ◽  
Gema Martínez-Navarro ◽  
Diana Gavilán

The evolution of technology and the digital empowerment of society have led to the proliferation of Audiovisual Content Webs (ACWs) where users can share information and experiences, along with other commercial resources. ACWs have led to significant changes in the way users can select and access audiovisual content. The design of these websites combines various features, including a user community, streamed content, ticket sales, and recommendations, among others. Each ACW has a specific profile with respect to the mentioned variables. The aim of this study is to identify the critical success factors for a ACW, i.e., which features and the form they should take to attract followers, thus increasing the capacity to prescribe and broadcast content. Using qualitative comparative analysis (QCA), a formal analysis technique that allows the identification of combinations that produce a certain result, a sample of the 12 most representative cinema websites in Spain is analyzed. The results indicate that the incorporation of content recommendation systems and the connection with streaming platforms through which the content can be accessed are key factors in the success of these ACWs. This work contributes academically to the knowledge and explanation of audience behavior in the new audiovisual scenario. From a professional point of view, relevant design suggestions are offered to platform creators. Finally, the limitations of this work are described, and future lines of research are considered. Resumen La evolución de la tecnología y el empoderamiento digital de la sociedad ha dado lugar a la proliferación de webs de contenidos audiovisuales (WCA) donde los usuarios comparten información y experiencias, junto a otros recursos comerciales. Las WCA han provocado cambios significativos en la forma en la que los usuarios pueden seleccionar y acceder a los contenidos audiovisuales. En su diseño, estas webs combinan varias prestaciones: comunidad de usuarios, contenidos en streaming, venta de entradas o recomendaciones, entre otros. Cada WCA presenta un perfil específico respecto a las variables descritas. El objetivo del presente trabajo es identificar los factores críticos de éxito de una WCA, es decir las prestaciones y la forma que deben adoptar para captar seguidores, aumentando con ello capacidad de prescripción y difusión de contenidos. Mediante el análisis cualitativo comparado (QCA), técnica formal de análisis que permite la identificación de combinaciones que producen un determinado resultado, se analiza una muestra de las 12 webs de cine más representativas en España. Los resultados indican que la incorporación de sistemas de recomendación de contenidos y la conexión con plataformas en streaming desde las que poder acceder a los contenidos son factores claves del éxito. El trabajo contribuye académicamente al conocimiento y la explicación de la conducta de la audiencia en el nuevo escenario audiovisual. Desde el punto de vista profesional se ofrecen sugerencias relevantes de diseño para los creadores de plataformas. Por último, se describen las limitaciones del trabajo y se plantean futuras líneas de investigación.


1997 ◽  
Vol 14 (1) ◽  
pp. 52-85
Author(s):  
Thomas E. Hill

Philosophers have debated for millennia about whether moral requirements are always rational to follow. The background for these debates is often what I shall call “the self-interest model.” The guiding assumption here is that the basic demand of reason, to each person, is that one must, above all, advance one's self-interest. Alternatively, debate may be framed by a related, but significantly different, assumption: the idea that the basic rational requirement is to develop and pursue a set of personal ends in an informed, efficient, and coherent way, whether one's choice of ends is based on self-interested desires or not. For brevity I refer to this as “the coherence-and-efficiency model.” Advocates of both models tend to think that, while it is sufficiently clear in principle what the rational thing to do is, what remains in doubt is whether it is always rational to be moral. They typically assume that morality is concerned, entirely or primarily, with our relations to others, especially with obligations that appear to require some sacrifice or compromise with the pursuit of self-interest.


2017 ◽  
Vol 887 ◽  
pp. 012061
Author(s):  
Junkai Yi ◽  
Yacong Zhang ◽  
Mingyong Yin ◽  
Xianghui Zhao

2013 ◽  
Vol 765-767 ◽  
pp. 998-1002
Author(s):  
Shao Xuan Zhang ◽  
Tian Liu

In view of the present personalized ranking of search results user interest model construction difficult, relevant calculation imprecise problems, proposes a combination of user interest model and collaborative recommendation algorithm for personalized ranking method. The method from the user search history, including the submit query, click the relevant webpage information to train users interest model, then using collaborative recommendation algorithm to obtain with common interests and neighbor users, on the basis of these neighbors on the webpage and webpage recommendation level associated with the users to sort the search results. Experimental results show that: the algorithm the average minimum precision than general sorting algorithm was increased by about 0.1, with an increase in the number of neighbors of the user, minimum accuracy increased. Compared with other ranking algorithms, using collaborative recommendation algorithm is helpful for improving webpage with the user interest relevance precision, thereby improving the sorting efficiency, help to improve the search experience of the user.


Sign in / Sign up

Export Citation Format

Share Document