Author : S.Kavishree 1
Date of Publication :12th April 2017
Abstract: In the recent years, social media have been emerged as major platforms for sharing information in the medical field, business, education etc. The existing system will generate a warning for adverse drugs reactions based on the negative comments from forums. The use of Latent Dirichlet Allocation modelling(LDA) in the existing system makes the data labelling process time-consuming and the polarity analysis is not done. But the proposed system uses Twitter to get the information and process on it. The information from the Twitter is extracted using Twitter API. Pre-processed tweets are stored in the database and those tweets are identified and classified whether it is based on drugs related tweets and diseases related tweets using Support Vector Machine classification(SVM). The user keywords can be predicted whether it is the best suggestion using polarity. Polarity detection is done by the keywords. Based on the number of positive tweets and the number of negative tweets it analyzes the best medicine. This system is very useful for the users to gain knowledge of the medicine
Reference :
-
- Altug Akay, Andrei Dragomir, Björn-Erik Erlandsson ,”Network- Based Modeling and Intelligent Data Mining of Social Media for Improving Care”,IEEE Journal of Biomedical and Health Informatics,Vol.19, Jan.2015
- Chih-Hua Tai, Zheng-Han Tan, Yue-Shan Chang,”Systematical Approach for Detecting the Intention and Intensity of Feelings on Social Network”, IEEE Journa of Biomedical and Health Informatics,Vol.20, Jul.2016
- Dingcheng Li, Cui Tao, Hongfang Liu,”OntologyBased Temporal Relation Modeling with MapReduce Latent Dirichlet Allocations for Big EHR Data”,Cloud and Green Computing (CGC) Second International Conference,Nov.2012
- Julio Cesar Louzada Pinto, Tijani Chahed,”Modeling Multi-topic Information Diffusion in Social Networks Using Latent Dirichlet Allocation and Hawkes Processes”,SignalImage Technology and Internet-Based Systems (SITIS) Tenth International Conference, Nov.2014
- Satya Katragadda, Harika Karnati, Murali Pusala,”Detecting adverse drug effects using link classification on twitter data”,Bioinformatics and Biomedicine (BIBM),IEEE International Conference,Nov.2015
- Sungrae Park, Doosup Choi, Wonsung Lee,”Disease-medicine topic model for prescription record mining”,Systems, Man and Cybernetics (SMC) IEEE International Conference,Oct.2014
- Xiao Xu, Tao Jin, Zhijie Wei,”TCPM: Topic-Based Clinical Pathway Mining”,Connected Health: Applications, Systems and Engineering Technologies (CHASE) IEEE First International Conference,Jun.2016
- Xiaoping Zhang, Xuezhong Zhou, Houkuan Huang,”A hierarchical symptom-herb topic model for analyzing traditional Chinese medicine clinical diabetic data”,Biomedical Engineering and Informatics (BMEI), 3rd International Conference,Oct.2010
- Yang Peng, Melody Moh, Teng-Sheng Moh,”Efficient adverse drug event extraction using Twitter sentiment analysis”,Advances in Social Networks Analysis and Mining (ASONAM), IEEE/ACM International Conference,Aug.2016
- Yi-Yu Hsu, Hung-Yu Kao,”Curatable Named-Entity Recognition Using Semantic Relations”,IEEE/ACM Transactions on Computational Biology and Bioinformatics,Vol.12,Jul.2015
- Yuji Zhang, Dingchen Li, Cui Tao,”An integrative computational approach to identify disease-specific networks from PubMed literature information”,Bioinformatics and Biomedicine (BIBM), 2013 IEEE International Conference,Dec.2013