| KEYWORD |
Deep Learning Tourist Recommender System Powered by Big 5 Personality Traits
Parole chiave NATURAL LANGUAGE PROCESSING, SUMMARIZATION
Riferimenti MAURIZIO MORISIO
Riferimenti esterni Giuseppe Rizzo, ISMB
Gruppi di ricerca GR-16 - SOFTWARE ENGINEERING GROUP - SOFTENG
Tipo tesi EXPERIMENTAL
Descrizione The undergraduate will research on recommending tourist activities leveraging the traces that a Twitter user shares publicly using tweets, likes, and retweets. In this thesis we aim to move significantly further the recommender system field tailoring recommendations leveraging both the demographics information and personal traces that is shared on Twitter. The recommender system will learn from several examples of tourist activities and generate a deep neural network that models both travel context and time.
The thesis will be structured as follows:
problem formulation: objective function, data structures and resources to be used;
algorithm design and approach implementation according to software engineering best practices;
in-lab testing verification with real data and measurement of the goodness of the approach.
The system will then be able to overcome the typical cold-start problem of any recommender system by only using the Twitter handle of the user and generating automatically a list of user profiles and personal interest features that will be used to recommend the desired item to be proposed to the final user.
The undergraduate will benefit from being immersed in a research environment. It’s a unique setting to get into a research mindset with a strong push for innovation. At the end of the thesis the undergraduate will be able to master recommender systems, data semantics and neural networks. As additional benefit, she/he will use proficiently control version systems, continuous integration systems, remote deploying and monitoring techniques.
Conoscenze richieste python, java, REST
Scadenza validita proposta 31/01/2019
PROPONI LA TUA CANDIDATURA