Personality-based recommendationhuman curiosity applied to recommendation systems using implicit information from social networks

  1. Menk Dos Santos, Alan
Dirixida por:
  1. Laura Sebastiá Tarín Director

Universidade de defensa: Universitat Politècnica de València

Fecha de defensa: 03 de decembro de 2018

Tribunal:
  1. Eduardo Sánchez Vila Presidente
  2. Soledad Valero Cubas Secretario/a
  3. Juan Antonio Recio García Vogal

Tipo: Tese

Resumo

In daily life, people usually rely on recommendations, traditionally given by other people (family, friends, etc.) for their most varied decisions. In the digital world, this is not different, given that recommender systems are present everywhere in such a way that we no longer realize. The main goal of these systems is to assist users in the decision-making process, generating recommendations that are of their interest and based on their tastes. These recommendations range from products in e-commerce websites, like books to read or places to visit to what to eat or how long one should walk a day to have a healthy life, who to date or who one should follow on social networks. And this is an increasing area. On the one hand, we have more and more users on the internet whose life is somewhat digitized, given than what one does in the "real world" is represented in a certain way in the "digital world". On the other hand, we suffer from information overload, which can be mitigated by the use of recommendation systems. However, these systems also face some problems, such as the cold start problem and their need to be more and more "human", "personalised" and "precise" in order to meet the yearning of users and companies. In this challenging scenario, personality-based recommender systems are being increasingly studied, since they are able to face these problems. Some recent projects have proposed the use of the human personality in recommenders, whether as a whole or individually by facet in order to meet those demands. Therefore, this thesis is devoted to this new area of personality-based recommendation, focusing on one of its most important traits, the curiosity. Additionally, in order to exploit the information already present on the internet, we will implicitly obtain information from social networks. Thus, this work aims to build a better experience for the end user through a new approach that offers an option for some of the gaps identified in personality-based recommendation systems. Among these gap improvements, the use of social networks to feed the recommender systems soften the cold start problem and, at the same time, it provides valuable data for the prediction of the human personality. Another found gap is that the curiosity was not used by any of the studied recommender systems; almost all of them have used the overall personality of an individual through the Big Five personality traits. However, psychological studies confirm that the curiosity is a relevant trait in the process of choosing an item, which is directly related to recommendation systems. In summary, we believe that a recommendation system that implicitly measures the curiosity and uses it in the process of recommending new items, especially in the tourism sector, could clearly improve the capacity of these systems in terms of accuracy, serendipity and novelty, allowing users to obtain positive levels of satisfaction with the recommendations. This thesis begins with an exhaustive study of the state of the art, where we highlight works about recommender systems, the human personality from the point of view of traditional and positive psychology and how these aspects are combined. Then, we develop an online application capable of implicitly extracting information from the user profile in a social network, thus generating predictions of one or more personality traits. Finally, we develop the CURUMIM system, able to generate online recommendations with different properties, combining the curiosity and some sociodemographic characteristics (such as level of education) extracted from Facebook. The system is tested and assessed within the tourism context by real users. The results demonstrate its ability to generate novel and serendipitous recommendations, while maintaining a good level of accuracy, independently of the degree of curiosity of the users.