Mining of Medical Trends Using Social Networks

Mining of Medical Trends Using Social Networks

Shruti Kohli (Birla Institute of Technology, India) and Sonia Saini (Birla Institute of Technology, India)
DOI: 10.4018/978-1-5225-6915-2.ch036
OnDemand PDF Download:
No Current Special Offers


Recent work in machine learning and natural language processing has studied the content of health related information in tweets and demonstrated the potential for extracting useful public health information from their aggregation. Social intelligence derived from health content has become of significant importance for various applications, including post-marketing drug surveillance, competitive intelligence, medicine reviews and to assess health-related opinions and sentiments. Further, the quantity of medical information in the media such as tweets on Twitter, Facebook or medical blogs is growing at an exponential rate. Medical data such as health records, drug data, etc. has become major candidates for Big Data analysis and thus exploring this content has become a necessity for organizations. However, the volume, velocity, variety, and quality of online health information present challenges, necessitating enhanced facilitation mechanisms for medical social computing. The objective of this chapter is to discuss the possibility of mining medical trends using Social Networks.
Chapter Preview


Social Network is a social structure comprising of individuals (or organizations) interconnected by one or more specific types of interdependencies such as kinship, exchange of financial data (e.g. SWIFT code), communication exchange, and other information or knowledge processing entities. It is based on an assumption of the importance of relationships among interacting units (Wasserman, S. and K. Faust, 1994). Social Network Analysis is the application of graph theory to comprehend, classify and quantify relationships in a social network. Social Network Analysis (SNA) relates to mapping, understanding, and analysing interactions across a set of people. Social network mining approaches tend to be founded on graph mining or network analysis techniques. Due to the evident recent big data surge due to increased consumer connectivity via medium of mobiles, tablets and other portable devices there is a growing need for social network analysis to understand more about the customers and their communities and enhance existing reports, modelling tools, and methodologies with social metrics(Taxidou,2013). In information diffusion in a social network, we study information diffusion in complex networks. Information can be anything from a quote, to rich text or media. Information diffusion study involves how information cascades in a network over a period of time. For organizations, such information diffusion analysis results in competitive intelligence, deeper customer insight and buying behaviour patterns. Information Diffusion analytics help in direct establishment of temporal information diffusion patterns in which social groups are more likely to recommend products, or form opinions, which can be further mined by decision support systems for business benefits resulting in increased sales/ returns for an organization.

Various applications for such analysis include optimization of supply chain for big e-tailers such as Amazon, Walmart etc., decision support system for HR and human capital retention, and market research survey analysis. In the UK, there has been renewed interest in the application of this theory in the field of health care. Research funded by the NIHR (National Institute for Health Research) Service Delivery and Organization Programme and more recently the development of NIHR Collaborations for Leadership in Applied Health Research and Care (CLAHRCs), has refocused attention on the role of social interactions and networks in the ability of health service organizations to identify and exploit knowledge from outside the National Health Service (NHS) (Chambers et al., 2002).

Complete Chapter List

Search this Book: