Are you what you eat?: Learning user tastes and recipe nutrition for rating prediction in context
The Faculty of Informatics is pleased to announce a seminar given by Morgan Harvey
DATE: Friday, November 23rd 2012
PLACE: USI Università della Svizzera italiana, room A24, Red building (Via G. Buffi 13)
Poor nutrition is one of the major causes of ill-health and death in the western world and is caused by a variety of factors including lack of nutritional understanding and preponderance towards eating convenience foods. As part of the VAMOS project, we wish to build systems which can recommend nutritious meal plans to users, however 2 crucial pre-requisites are to be able to accurately estimate the nutritional properties of recipes and to recommend dishes that people will actually like. In this talk I will first demonstrate systems that can estimate nutritional content based only on the inconsistently-structured recipes found on the Internet. Secondly, by analysing the results of a longitudinal study (n=124) I investigate key factors contributing to how recipes are rate, identifying a number of important contextual factors which can influence the choice of rating. Based on this analysis, it will be shown how it is possible to construct several recipe recommendation models that are able to leverage understanding of user’s likes and dislikes in terms of ingredients and combinations of ingredients and in terms of nutritional content. Finally I will discuss how the results of this research can be utilised in future work, including building automated weekly recipe plans.
Morgan Harvey studied Computer Science at the University of Strathclyde where he completed his PhD in 2011 under the supervision of Prof. Ian Ruthven. Between July 2011 and October 2012 he worked as leading post-doctoral researcher at the Chair for Artificial Intelligence in Erlangen, Germany. There he was responsible for the successful completion of a number of projects, including the VAMOS healthcare project. He publishes in a number of fields of Information Retrieval and Machine Learning with a focus on understanding and supporting the needs of users in different search and information-seeking situations. His work focusses particularly on the areas of socially-generated media, personalisation and recommender systems.
HOST: Prof. Fabio Crestani