Exploring Identifiers of Research Articles Related to Food and Disease using Artificial Intelligence

The research project aims to understand how variation in writing styles and flexibility of text mining methods control their ability to extract useful information from articles about food and health. Those areas of study are significant because they incorporate features of text mining methods and food-health articles. The project will build a database and mining tools that would change the way we search and collect information from scientific publications and the way we analyze this information for further applications. The strategy to achieve the project’s goal is to engage several teams of undergraduate students in Applied Computing to develop a food-health portal. Some teams will develop text mining tools and others use these tools and existing data-mining tools to extract the portal contents from articles about food-health. The information extracted will create and inform a database of food/health relationships. The project addresses several issues of central importance to the success of text mining techniques extracting useful food-health information for serving society now and in future. Those include: how writing style of an article is determined automatically, how main topic of an article/document is identified automatically, how useful information is extracted from an article/document to help national and international researchers in conducting further research, how available food articles can be quickly utilized to help the society, how undergraduate students gain skills required for extracting useful information from the huge amount of data available on the internet