{"title":"CitizenPulse: A Text Analytics framework for Proactive e-Governance - A Case Study of Mygov.in","authors":"Ankit Lamba, Deepak Yadav, A. Lele","doi":"10.1145/2888451.2888463","DOIUrl":"https://doi.org/10.1145/2888451.2888463","url":null,"abstract":"Indian Citizens are beginning to express themselves via social media on a regular basis on various issues. Government of India have started an initiated called as Mygov.in as a collaborative portal where citizens can voice their opinions via free form comments. Analyzing this free form data is a huge challenge. In this paper we present a work in progress called as CitizenPulse framework, capable of performing text analytics on unstructured text using off-the-shelf text analytics components like Named Entity Recognition, Part of Speech and Stemming to name a few. Apart from integrating the text analytics components, CitizenPulse framework abstracts these building blocks as Object, and such different objects can be dragged, dropped and connected to construct a text analytics pipeline called as Analytics Softcore. As a case study we report the analysis of the Mygov.in portal specifically for the topic of Cleanliness in School Curriculum.","PeriodicalId":136431,"journal":{"name":"Proceedings of the 3rd IKDD Conference on Data Science, 2016","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123728898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Some algorithms for correlated bandits with non-stationary rewards: Regret bounds and applications","authors":"Prathamesh Mayekar, N. Hemachandra","doi":"10.1145/2888451.2888475","DOIUrl":"https://doi.org/10.1145/2888451.2888475","url":null,"abstract":"We first propose an online learning model wherein rewards for different actions/arms used by the user can be correlated and the reward stream can be non-stationary. Thus, this extends the standard multi-armed bandit learning model. We propose two algorthims, Greedy and Regression based UCB, that attempt to minimize the expected regret. We also obtain non-trivial upper bounds for the expected regret through theoretical analysis. We also provide some evidence for sub-polynomial increase in expected regret upon appropriate tuning of algorithm input parameters. These models are motivated by the problem of dynamic pricing of a product faced by a typical online retailer.","PeriodicalId":136431,"journal":{"name":"Proceedings of the 3rd IKDD Conference on Data Science, 2016","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126568183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}