Computational Data Analytics on the Web for Better Food Decision Making

Christoph Trattner is an Associate Professor at the University of Bergen in the Information Science & Media Studies Department. Previously, he was an Asst. Prof. at MODUL University Vienna in the New Media Technology Department. He also founded and led the Social Computing department at the Know-Center, Austria’s research competence for data-driven business and big data analytics. He holds a Ph.D. in Computer Science and Telematics from Graz University of Technology (Austria).

Christoph’s research background includes Applied Machine Learning, Predictive Modeling, Recommender Systems, Social Networks Analysis, Human Computer Interaction and Data Science in particular. He is leading an international research effort that tries to understand, predict and change online food preferences to tackle health-related food issues such as diabetes or obesity. Since 2010, he published two books and over 90 scientific articles in top conferences and journals including, e.g., JASIST, UMUAI, TiiS, ComCom, EPJ Data Science, WWW, ICWSM. He holds several Best Paper/Poster Awards and Nominations, including, the Best Paper Award Honorable Mention in 2017 at the prestigious WWW conference series.

Abstract:
According to the World Health Organization around 80% of cases of heart disease, strokes and type 2 diabetes could be avoided if people were to implement a healthier diet. Computational data analytics approaches have been touted as a valuable asset in achieving the ambitious goal of understanding user behavior and being able to develop intelligent online systems, which can positively influence people’s food choices. In this talk, I will present our latest research on computational data analytics approaches to understand, predict and potentially change food decision making in an online context. First, I will show to what extent online food interactions can be linked to real-world health issues such as obesity on a large-scale. After that, I will show how people upload, bookmark or rate online recipes in large online food communities and how contextual factors and biases such as seasonality, temporality, social context or presentation of recipes have an impact Christoph Trattner Associate Professor @ University of Bergen on popularity and how they are perceived. Furthermore, I will reveal to what extent these factors and biases can be exploited to model and predict the users’ online food choices. To conclude, I will present some preliminary work aiming to nudge people towards food choices and recent work on learning to recommend similar items from human judgments in that domain employing crowdsourcing.