Intelligent Strategy and Security in Education: Big Data (Text Analytics)

Intelligent Strategy and Security in Education: Big Data (Text Analytics)

Samson Oluwaseun Fadiya (The American University of Cyprus, Cyprus)
DOI: 10.4018/978-1-5225-8976-1.ch004

Abstract

Text analytics applies to most businesses, particularly education segments; for instance, if association or university is suspicious about data secrets being spilt to contenders by the workers, text analytics investigation can help dissect many employees' email messages. The massive volume of both organized and unstructured data principally started from the web-based social networking (media) and Web 2.0. The investigation (analysis) of messages online, tweets, and different types of unstructured text data constitute what we call text analytics, which has been developed during the most recent few years in a way that does not shift, through the upheaval of various algorithms and applications being utilized for the processing of data alongside the protection and IT security. This chapter plans to find common problems faced when using the different medium of data usage in education, one can analyze their information through the perform of sentiment analysis using text analytics by extracting useful information from text documents using IBM's annotation query language (AQL).
Chapter Preview
Top

Introduction

The examination of language and communication has been fundamental to the progression of text analytics as the astounding parts of semantics, which means, and the point must be to some extent motorised. To examine a past loaded with phonetics, one would consider pre-Socratic what's increasing, platonic eras (Gee, J.P., 2010). Notwithstanding whether oral or sign, language has been fundamental in the exchange and securing of data. One could see Discourse Analysis as a paste to connect phonetics to computation. It incorporates the examination of correspondence from any combination of sources with a real objective to recognise not just the typical structures to the exchange of data yet. Also, to distinguish more complex concepts, for instance, an exchange of partnership, distinguish, and activity (Clarke, Nelson, & Stoodley, 2013)

Notwithstanding the creating predominance of, development advancement in, and openings by text analytics, it had been transferred to somewhat cut of some current course, for instance, data mining. Research has, for the most part, focused on the structure, algorithms, and design (architecture) of text mining and related development (Goharian, Grossman, Frieder, & Raju, 2004) in courses offered from Software engineering divisions in Engineering schools. A review of educational or pedagogical techniques for data recovery (Fernández-Luna, Huete, MacFarlane, & Efthimiadis, 2009) was restricted to Software engineering and Library Information Science departments; Data Frameworks from Business colleges were rejected. In both the reported fields, the interest was in how to create tags, either for dictionaries and thesauri or to insert into software (Fernández-Luna, Huete, MacFarlane, and Efthimiadis, 2009). An illustration database for data mining (Gee, 2010) revealed that normal subjects here are often at the algorithmic. The business setting of how to utilise these thoughts and developments by examiners who can translate the results to impact essential proposals of business to regard has not been addressed. However regularly the setting has been on changing unstructured text into the quantitative edge(frame) to apply traditional quantifiable investigation. Working with databases will allow familiarity with structured data. Computers have been working with these systems for a very long time, be that as it may, the amount of stored structured data is less in nature when compared to unstructured data like some blog posts, tweets, documents created, and emails sent daily are all unstructured or semi-structured data. So, what can all this data do for us? For one, documents often contain facts.

Complete Chapter List

Search this Book:
Reset