Source: Shutterstock

Scope and aim

The United Nations states “End hunger, achieve food security and improved nutrition and promote sustainable agriculture" as one of its sustainable development goals by the target date of 2030. To achieve these goals, global food and agriculture systems will require profound changes, in which big data and AI technologies can play significant roles. In the past decade, a huge amount of work has been done in biomedical predictive modelling. This would not be possible without the existence of diverse biomedical vocabularies and standards, which play a crucial role in understanding biomedical information, together with a large amount of biomedical data collected (e.g., drug, diseases and other treatments) from numerous sources. While there are extensive resources available for the biomedical domain, the food and nutrition domain is relatively low resourced. For example, there is no publicly available annotated corpus with food and nutrient concepts, and there are few food named-entity recognition systems for the extraction of food and nutrient concepts. In addition, the available food ontologies are developed for a very narrow use cases, and there are no links between these ontologies that can be used for food and nutrition data management.

In this workshop, we aim to focus primarily on methodologies for the management and analysis of food- and nutrition-related big data. BFNDMA 2019 will consider original and unpublished research articles that propose bold steps towards addressing the challenges of data management and analysis of food- and nutrition-related data. We welcome data-driven and rule-based approaches related to food and nutrition problems.

Topics of Interest related to Food and Nutrition

  • Information retrieval, information extraction, natural language processing techniques, computer vision and artificial intelligence;
  • Data normalization;
  • Knowledge representation;
  • Ontologies, vocabularies and ontology design patterns, with a focus on describing the modelling process;
  • Crowdsourcing task designs that have been used and can be (re)used for building resources such as gold standards;
  • Data mining and knowledge discovery
  • Analytics, including social media, text, or structured datasets;
  • Recommendation of food, menu, or food- and nutrition-related habits;
  • Policy analysis and recommendations relevant to citizens and governments;
  • Wearable devices, quantified-self data for food, nutrition, and health.

Invited Speakers

Prof. Karl Aberer, PhD


Ecole polytechnique fédérale de Lausanne (EPFL), Lausanne, Switzerland

Title: Explorations of the Food Information Universe

In this talk I will present several projects in which we analysed publicly available nutrition-related data. First I will report on the outcomes of analysing social media discussions related to processed food at large scale. This work resulted in relevant findings from an industrial perspective, but also set the pathway for constructing a social media analytics platform that we have commercialised in the meantime. Then I will present work on evaluating automatically the credibility of Web articles related to health related topics. This work revealed insights on the relative importance of various content and social features of Web content that can serve as indicators for credibility. Finally, I will introduce our current work on evaluating the quality of news reports on scientific findings in health and nutrition. In this work we are tracking the diffusion of scientific results through news and social media, and are developing methods to semi-automatically and automatically rate the article quality.

Oshani Seneviratne, PhD, Director of Health Data Research


Rensselaer Polytechnic Institute, USA

Title: FoodKG: A Semantics-Driven Knowledge Graph for Food Recommendation

The proliferation of recipes and other food information on the Web presents an opportunity for discovering and organizing diet-related knowledge into a knowledge graph. Currently, there are several ontologies related to food, but they are specialized in specific domains, e.g., from an agricultural, production, or particular health condition point-of-view. There is a lack of a unified knowledge graph that is oriented towards consumers who want to eat healthily, and who need an integrated food suggestion service that encompasses food and recipes that they encounter on a day-to-day basis, along with the provenance of the information they receive. In this talk, I will introduce our software toolkit that can be used to create a unified food knowledge graph that links the various silos related to food while preserving the provenance information. I will also describe how this knowledge graph has been utilized in a cognitive agent that can perform natural language question-answering using the knowledge graph.


    Please submit a full-length paper (up to 10 page IEEE 2-column format), or short or position paper (2-4 page IEEE 2-column format), through the online submission system.
    Paper Submission Page Papers should be formatted to IEEE Computer Society Proceedings Manuscript Formatting Guidelines
    (see link to "formatting instructions" below).

    Formatting instructions
    Microsoft Word
    LaTex Formatting Macros

    In order to participate to this workshop, full or student registration of IEEE BigData 2019 is needed.

Important dates

  • Paper submission: Oct 20, 2019
  • Decision notification: Nov 1, 2019
  • Camera-ready submission: Nov 15, 2019
  • Workshop: Dec 9-12, 2019


Tome Eftimov, PhD

Department of Biomedical Data Sciences,
Stanford University, CA, USA

Center for Population Health Sciences,
Stanford University, CA, USA

Bibek Paudel, PhD

Department of Biomedical Data Sciences,
Stanford University, CA, USA

Center for Population Health Sciences,
Stanford University, CA, USA

Prof. Barbara Koroušić Seljak, PhD

Computer Systems Depratment,

Jožef Stefan Institute, Ljubljana, Slovenia

Duccio Cavalieri, University of Florence, IT
Chris Evelo, Maastricht University, NL
Paul Finglas, Quadram Institute, UK
Hristijan Gjoreski, Ss. Cyril and Methodius University, MK
Martin Gjoreski, Jožef Stefan Institute, SI
Gordana Ispirova, Jožef Stefan Institute, SI
Dragi Kocev, Jožef Stefan Institute, SI
Peter Korošec, Jožef Stefan Institute, SI
Fabio Mainardi, Nestle Institute of Health Science S.A, Lausanne, CH
Panče Panov, Jožef Stefan Institute, SI
Petar Ristoski, IBM Research, CA, USA
Lisa Goldman Rosas, Stanford University, CA, USA
Monika Simjanoska, Ss. Cyril and Methodius University, MK
Suzanne Tamang, Stanford University, CA, USA
Maria Traka, Quadram Institute Bioscience, UK
Erika Tribett, Stanford University, USA

Workshop on Big Food and Nutrition Data Management and Analysis
Monday, December 9, 9:00AM-5:30PM, Room: San Gabriel A, Chair: Tome Eftimov, Bibek Paudel and Barbara Koroušić Seljak
Welcome and Introduction
9:15AM-9:50AM Invited talk: FoodKG: A Semantics-Driven Knowledge Graph for Food Recommendation (Dr. Oshani Seneviratne)
9:50AM-10:10AM Comparing Semantic and Nutrient Value Similarities of Recipes (Gordana Ispirova)
10:10AM-10:30AM Coffee Break
10:30AM-10:50AM Exploring a standardized language for describing foods using embedding techniques (Gorjan Popovski)
10:50AM-11:10AM Semi-Automatic Crowdsourcing Tool for Online Food Image Collection and Annotation (Zeman Shao)
11:10AM-11:30AM Exploring Dietary Intake Data collected by FPQ using Unsupervised Learning (Nina Reščič)
11:30AM-12:05PM Invited talk: Explorations of the Food Information Universe( Prof. Karl Aberer)
12:05PM-1:30PM Lunch
1:30PM-1:50PM Food Waste Ontology: A Formal Description of Knowledge from the Domain of Food Waste (Riste Stojanov)
1:50PM-2:10PM From DIKW pyramid to graph database: a tool for machine processing of nutritional epidemiologic research data (Chen Yang)
2:10PM-2:30PM Optimization of arable land use towards meat-free and climate-smart agriculture: A case study in food self-sufficiency of Vietnam (Vladimir Kuzmanovski)
2:30PM-3:30PM Light Talks (5 min presentation for each poster) (8 accepted papers)
3:30PM-4:20PM Coffee Break
4:20PM-5:20PM Poster Presentation and Discussion (All accepted papers)
5:20PM-5:30PM Closing Remarks