A COMPARATIVE STUDY OF RECOMMENDER ALGORITHMS FOR A GASTRONOMIC SOCIAL NETWORK

Description: The always-growing popularity of social networks between the people and with a generation that takes a picture to everything they do or what they eat, generating a huge amounts of data. It is extremely difficult to deal with the available information without a tool support. The recommender systems are such tools; nowadays these are very popular because they process the information and suggest items, social elements, products or services that are likely to be of a user's interest. Onfan (onfan.com) is a gastronomic social network based in Barcelona that feeds on the contents that users assess and share about the specialties of any dining establishment where the users have visited. The provision of new functionality in the site to assist and suggest users which specialty should taste, has become a priority to improve the user's satisfaction. To add this capability, we require to understand the user activities for a correct computation of ecommendations based on their preferences. Here, we report an analysis of real user ratings on a set of recipes in order to judge the applicability and practicality of custom algorithms, already tested to compute recommendations in social networks.

Get full text: http://repositorio.educacionsuperior.gob.ec/handle/28000/2015