Smart Recommendation System for Off-the Shelf Medicines

  • Authors

    • Ratna Sathappan
    • Tholu Sai Indira
    • A Meenapriyadarsini
    2018-04-25
    https://doi.org/10.14419/ijet.v7i2.24.12126
  • .

  • Abstract

    Internet usage has been at an all-time high from 2000’s vintage years. The people who have access to the internet use it for numerous reasons such as social networking, marketing, promoting, enhancing businesses, consultancy, research, gaming and the list goes on. In the recent years, Review websites have flourished, where people share their opinion about a product, with an increase in response rate and reliability. Recommendations are made by mining data from review websites. Traditional Recommendation systems are limited as they only consider certain metrics, such as product purchase details, product category. Recommendation systems are yet to gain popularity in the medical field. These days most patients are unable to figure out the medication that works in healing them in the best way possible, hence they turn to review websites in order to obtain a second opinion on the prescribed medication. In this work, we have developed a smart recommendation system for off-the Shelf Medical Drugs using machine learning and data analytics based on patient feedback. The patient feedback is unstructured data which is processed using data analytic tools. After which machine learning is used to recommend the best fit and compare the drugs. In this work, we predict the impact of a drug/ medicine on the patient to whom the medication was prescribed, using data mining techniques. Firstly, we detect the user’s polarity (positive/ negative/neutral) based on the patient feedback for a certain drug using sentiment analysis and opinion mining following which we use machine learning algorithms to track sentiment variation and to make a recommendation based on user polarity

  • References

    1. [1] Xiaojiang Lei, Xueming Qian, Member, IEEE, and Guoshuai Zhao, “Rating Prediction Based on Social Sentiment from Textual Reviewsâ€, IEEE transactions on multimedia ,Vol. 18,No. 9, September 2016.

      [2] A. Ng, A. Zheng, and M. Jordan, “Stable algorithms for link analysis,†in Proc. SIGIR Conf. Inform. Retrieval, New Orleans, Louisiana LO, USA, 2001, pp. 258–266.

      [3] B. Taskar, M. Wong, P. Abbeel, and D. Koller, “Link prediction in relational data,†in Proc. Adv. Neural Inform. Process. Syst., Vancouver, B.C. Canada, 2003.

      [4] C. Corley, D. Cook, A. Mikler, and K. Singh, “Text and structural data mining of influenza mentions in web and social media,â€Int. J. Environ. Res. Public Health, vol. 7, pp. 596– 615, Feb. 2010.

      [5] D. Liben-Nowell and J. M. Kleinberg, “The link prediction problem for social networks,â€J. Am. Soc. Inform. Sci. Technol., vol. 57, pp. 556–559, May 2007.

      [6] L. Dunbrack, “Pharma 2.0 – social media and pharmaceutical sales and marketing,†inProc. Health Ind. Insights, 2010, p. 7.

      [7] Rennie, J.D., et al.: Tackling the poor assumptions of naive bayes text classifiers. In: Machine Learning-International Workshop then Conference, vol. 20(2) (2003).

      [8] Vivek Narayana, Ishan Arora, Arjun Bhatia, “Fast and Accurate Sentiment Classification Using an Enhanced Naïve Bayes Modelâ€, International Conference on Intelligent Data Engineering and Automated Learning.

      [9] ] R. Salakhutdinov and A. Mnih, “Probabilistic matrix factorization,†in Proc. NIPS, 2007, pp. 1257–1264.

      [10] X. Yang, H. Steck, and Y. Liu, “Circle- based recommendation in online social networks,†in Proc. 18th ACM SIGKDD Int. Conf. KDD, Aug. 2012, pp. 1267–1275.

      [11] M. Jiang et al., “Social contextual recommendation,†in Proc. 21st ACM Int. Conf. Inf. Knowl. Manage, 2012, pp. 45– 54.

      [12] M. Jamali and M. Ester, “A matrix factorization technique with trust propagation for recommendation in social networks,†in Proc. ACM Conf.Recommender Syst., 2010, pp. 135–142.

      [13] Z. Fu et al., “Achieving efficient cloud search services: Multi-keyword ranked search over encrypted cloud data supporting parallel computing,†IEICE Trans. Commun., vol. 98, no. 1, pp. 190–200, 2015.

      [14] G. Ganu, N. Elhadad, and A Marian, “ Beyond the stars: Improving rating predictions using Review text content,†in Proc. 12th Int. Workshop Web Databases, 2009, pp. 1–6.

      [15] J. Xu, X. Zheng, and W. Ding, “Personalized recommendation based on reviews and ratings alleviating the sparsity problem of collaborative filtering,†in Proc. IEEE 9th Int. Conf. e-Bus. Eng., Sep. 2012, pp. 9–16.

      [16] X. Qian, H. Feng, G. Zhao, and T. Mei, “Personalized recommendation combining user interest and social circle,†IEEE Trans. Knowl. Data Eng., vol. 26, no. 7, pp. 1763–1777, Jul. 2014.

      [17] S. Li et al., “Sentiment classification and polarity shifting,†in Proc. 23rd Int. Conf. Comput. Linguistics, 2010, pp. 635–643.

      [18] B. Sun and V. Ng, “Analyzing sentimental influence of posts on social networks,†in Proc. IEEE 18th Int. Conf. Comput. Supported Cooperative Work Des, May 2014, pp. 546– 551.

      [19] G. Zhao, X. Qian, and X. Xie, “User- service rating prediction by exploring social users’ rating behaviors,†IEEE Trans. Multimedia, vol. 18, no. 3,pp. 496–506, Mar. 2016

      [20] D. Vilares, M. A. Alonso, and C. Gomezrodr Ì Ìıguez, “A syntactic approach for opinion mining on Spanish reviews,†Natural Lang. Eng., vol. 21, no. 1, pp. 1–25, 2014 [21]Sanjiv R.Das and Mike Y Chen, “Yahoo! For Amazon reference: Sentiment Extraction from Small Talk on the Web, May 2,2004.

      [21] Erwan Le Martelot and Chris Hanki, “Multi scale Community detection using stability as optimization criterion in a Greedy Algorithmâ€, Imperial College of London. Department of Computing

      [22] Jayashri Khairnar and Mayura Khairnar, “Machine Learning Algorithms for Opinion Mining and Sentiment Classificationâ€,Department of Computing, Pune University, MIT Academy of Engineering, Pune.

      [23] B. Sampath Kumar and Dr D. Bhanu Shree Reddy,†An Analysis on Opinion Mining Techniques and Tools†,VIT Business School, VIT University.

      [24] Altug Akay School of Technology and Health, Royal Institute of Technology, Stockholm, Sweden Andrei Dragomir School of Technology and Health, Royal Institute of Technology, Stockholm, Sweden Björn-Erik Erlandsson Department of Biomedical ngineering, University of Houston, Houston, TX, USA Network based modeling and intelligent data mining of socialmedia for improvingcare.

      [25] T. Padmapriya and V. Saminadan, “Priority based fair resource allocation and Admission Control Technique for Multi-user Multi-class downlink Traffic in LTE-Advanced Networksâ€, International Journal of Advanced Research, vol.5, no.1, pp.1633-1641, January 2017.

      [26] M. Rajesh, Manikanthan, “ANNOYED REALM OUTLOOK TAXONOMY USING TWIN TRANSFER LEARNINGâ€, International Journal of Pure and Applied Mathematics, ISSN NO:1314-3395, Vol-116, No. 21, Oct 2017.

      [27] S.V. Manikanthan , T. Padmapriya “An enhanced distributed evolved node-b architecture in 5G tele-communications network†International Journal of Engineering & Technology (UAE), Vol 7 Issues No (2.8) (2018) 248-254.March2018

  • Downloads

  • How to Cite

    Sathappan, R., Sai Indira, T., & Meenapriyadarsini, A. (2018). Smart Recommendation System for Off-the Shelf Medicines. International Journal of Engineering & Technology, 7(2.24), 417-420. https://doi.org/10.14419/ijet.v7i2.24.12126

    Received date: 2018-04-25

    Accepted date: 2018-04-25

    Published date: 2018-04-25