• Jul 03, 2017 News!Good News! Since 2017, IJMLC has been indexed by Scopus!
  • Jul 06, 2017 News!Vol.7, No.2 has been published with online version.   [Click]
  • Jul 01, 2017 News!Vol.7, No.1 has been published with online version.   [Click]
Search
General Information
Editor-in-chief
Dr. Lin Huang
Metropolitan State University of Denver, USA
It's my honor to take on the position of editor in chief of IJMLC. We encourage authors to submit papers concerning any branch of machine learning and computing.
IJMLC 2016 Vol.6(2): 117-122 ISSN: 2010-3700
DOI: 10.18178/ijmlc.2016.6.2.584

Insights Exploration of Structured and Unstructured Data and Construction of Automated Knowledge Banks

Arvind Maurya, Yogesh Gupta, and Stuti Awasthi
Abstract—Enterprise data is in abundance in form of knowledge articles, forums, blogs and open internet. However, this data has not been tapped effectively to bring out real and differentiated values to help enterprises as well as their customers. In this paper we have described how contextual text mining can drastically improve productivity of support engineers and also enable customer to do self-resolution of commonly occurring problems. Average resolution time for user problems can range between few hours to more than a week depending on ease of availability of relevant information and knowledge of engineer handling the problem. In order to significantly reduce the response time, we approached it through automating the construction of knowledge banks based on multiple contexts present in a single source. Knowledge identification and extraction are two separate solution arcs and information flows from one arc to another to build an optimal solution using both supervised and unsupervised learning techniques. We applied this solution for network division of a technology company and the experiment demonstrated reduction in response time and thereby productivity gains for support engineers by 30% over a period of 3 months.

Index Terms—Ngrams, stemming, feature extraction, stop words elimination, vector space model, naïve bayes, cosine similarity measure, canopy clustering, kmeans clustering, hadoop, mahout, mapreduce.

The authors are with HCL Technologies Ltd, A-8 and 9, Sector-60, Noida - 201301, UP, India (e-mail: maurya-a@ hcl.com, yogeshg@hcl.com, stutiawasthi@hcl.com).

[PDF]

Cite: Arvind Maurya, Yogesh Gupta, and Stuti Awasthi, "Insights Exploration of Structured and Unstructured Data and Construction of Automated Knowledge Banks," International Journal of Machine Learning and Computing vol.6, no. 2, pp. 117-122, 2016.

Copyright © 2008-2015. International Journal of Machine Learning and Computing. All rights reserved.
E-mail: ijmlc@ejournal.net