Thesis subject

Early Warning System for Allergens in Novel Foods Using Online Media Data (MSc)

There is a need to improve food supply sustainability and a key element for this, is moving to more plant-based and alternative (novel) protein sources. Therefore, it is crucial to understand the potential safety implications of such a dietary shift, and ensure approaches and tools are in place for risk assessment and risk management. This thesis will focus on the food allergic consumer, aiming to improve understanding of their acceptance and trust of novel foods and how to monitor for, and manage, any potential allergenicity risks.

Short description

Food allergy currently affects 20 million Europeans and costs the health care system ~55 billion Euros annually . The economic impact of food allergy is also substantial. The direct and indirect costs related to food allergy has globally been estimated to an individual-level direct medical cost of ~ € 2081 and a household-level out-of-pocket cost (e.g., special diets) of ~ €4881 per year. Apart from economic impact, food allergy also has a strong impact on the quality of life of patients and their families, the extensive dietary constraints can lead to psychosocial burden, eating disorders, deficiencies, and growth retardation.
In this project, we will focus on the food allergic consumer, aiming to improve understanding of their acceptance and trust of novel foods and how to monitor for, and manage, any potential allergenicity risks. This project aims on leveraging the power of AI to develop an early warning system for allergens in novel foods using online media data. With the emergence of new food products and ingredients, there is a need for efficient methods to identify potential allergens and ensure the safety of consumers with food allergies. By utilizing AI, including natural language processing, machine learning, and data mining, this study aims to analyze online media data to detect and monitor allergen-related information and provide timely warnings to both consumers and food regulatory authorities.


Objectives

  1. Collect and pre-process relevant online media data, including news articles, social media posts, food blogs, and reviews, focusing on discussions related to novel foods and potential allergens.
  2. Develop algorithms that can identify mentions of potential allergens, allergic reactions, food recalls, and safety concerns from the online media data.
  3. Develop an AI-based early warning system that monitors online media data in real-time and identifies emerging allergen-related issues in novel foods.

    Tasks

    The work in this master thesis entails:

    • Literature review: Conduct a review of existing research studies, on AI techniques, Early warning systems for allergens in novel foods, and prediction models.
    • Data collection and preparation: Collect and preprocess data from various sources.
    • AI models development: Apply natural language processing techniques to extract relevant information from the collected data. Train machine learning models using annotated data to classify allergen-related information into different categories. Design and implement an early warning system that continuously monitors online media data for allergen-related information.
    • Results reporting and documentation: Prepare a comprehensive report summarizing the research methodology, results, and conclusions.


    Literature

    • ver LA, Chadha AS, Doshi P, O'Dwyer L, Gupta RS. Economic burden of food allergy: A systematic review. Ann Allergy Asthma Immunol. 2019;122(4):373-80 e1.


    Requirements

    • Courses: Programming in Python (INF-22306), Data Science Concepts (INF-34306) or Machine Learning (FTE-35306)
    • Required skills/knowledge: Food and health, Machine Learning

      Key words: Artificial Intelligence, allergen management practices, consumer safety

      Contact person(s)

      Dr. Yamine Bouzembrak (yamine.bouzembrak@wur.nl)
      Prof. Bedir Tekinerdogan (bedir.tekinerdogan@wur.nl)