Prediction of Active Users and Location Surveillance to Study Diabetes Disease Dynamics
P. Vasudha Rani1, K. Sandhya Rani2
1P. Vasudha Rani, Research Scholar, Assistant Professor Sr, Department of CS IT, SPMVV, Tirupati, GMRIT (A.P), India.
2Dr. K. Sandhya Rani, Professor, Department of CS, SPMVV, Tirupati (A.P), India.
Manuscript received on 22 April 2019 | Revised Manuscript received on 01 May 2019 | Manuscript Published on 05 May 2019 | PP: 371-381 | Volume-8 Issue-2S2, May 2019 | Retrieval Number: B10790182S219/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Twitter is the source for a massive amount of spatiotemporal information about individuals propagating their opinions, feelings, suggestions, support, etc. These data can be utilized in a number of diverse fields to monitor and understand a range of social phenomena. One important and largely unexploited use of Twitter’s massive data feed is to utilize tweets as a means for understanding trends in public health. Twitter-based health research is a growing field funded by a diversity of organizations. As a part of the health-related research, here the task is to analyze Diabetes related User Activity and Location-specific postings to identify the Active Locations with more Active Users that generates more user Activity. This task requires geolocated tweets with user details and other information such as followers and follows. As a part of the health-related research, a model is proposed in this paper which focus on tracking and understanding the patterns of causes, affected diseases and suggested foods for the control and prevention of Diabetes in a comprehensive approach. For this work, the data source is a tweet source generated from individual and majority group twitter accounts working on Diabetes and related issues continuously. The proposed method uses an advanced data mining framework with a novel use of social media data retrieval and classification filtering to identify Active Locations & Users and understand how tweets from Active Users and Active Locations can be used to explore the prevalence of causes, affected other diseases, and healthy food suggestions for control and prevention of Diabetes.
Keywords: Active Users, Active Locations, Classification, Geolocated Diabetes Tweets, Patterns of Causes, Patterns of Affected Diseases.
Scope of the Article: Regression and Prediction