@inproceedings{7d8e1413753347cba6c99521d25870b3,
title = "Terms mining in document-based NoSQL: Response to unstructured data",
abstract = "Unstructured data mining has become topical recently due to the availability of high-dimensional and voluminous digital content (known as 'Big Data') across the enterprise spectrum. The Relational Database Management Systems (RDBMS) have been employed over the past decades for content storage and management, but, the ever-growing heterogeneity in today's data calls for a new storage approach. Thus, the NoSQL database has emerged as the preferred storage facility nowadays since the facility supports unstructured data storage. This creates the need to explore efficient data mining techniques from such NoSQL systems since the available tools and frameworks which are designed for RDBMS are often not directly applicable. In this paper, we focused on topics and terms mining, based on clustering, in document-based NoSQL. This is achieved by adapting the architectural design of an analytics-as-a-service framework and the proposal of the Viterbi algorithm to enhance the accuracy of the terms classification in the system. The results from the pilot testing of our work show higher accuracy in comparison to some previously proposed techniques such as the parallel search.",
author = "Lomotey, {Richard K.} and Ralph Deters",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 3rd IEEE International Congress on Big Data, BigData Congress 2014 ; Conference date: 27-06-2014 Through 02-07-2014",
year = "2014",
month = sep,
day = "22",
doi = "10.1109/BigData.Congress.2014.99",
language = "English (US)",
series = "Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "661--668",
editor = "Peter Chen and Peter Chen and Hemant Jain",
booktitle = "Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014",
address = "United States",
}