Please use this identifier to cite or link to this item: https://www.um.edu.mt/library/oar/handle/123456789/49285
Title: Implementing machine learning in a service desk department based on previous interactions : a study of sentiment analysis and opinion mining
Authors: Bartolo, Christopher
Keywords: Machine learning
Language and emotions -- Data processing.
Data mining
Computational linguistics -- Malta
Malta International Airport
Issue Date: 2019
Citation: Bartolo, C. (2019). Implementing machine learning in a service desk department based on previous interactions: a study of sentiment analysis and opinion mining (Bachelor's dissertation).
Abstract: This research work revolves around the study of implementing a machine learning system more precisely a Sentiment Analysis or Opinion Mining system in a Service Desk Department at a local IT support organisation in the Malta International Airport. The aim is to gather information from the service desk team itself regarding their opinions and attitude towards such a system as well as the organisations’ and clients’ would be interaction with such a system as a whole. Subsequently it was identified the necessary steps and precautions such organisations might need to take preceding the implantation of a Sentiment Analysis system. Through the case study which consisted of a focus group as well as observation session by the researcher, various Socio Technical Theory mechanisms were researched and studied including the current tools at hand as well as the current relationships between all personnel in the company. Change management was also discussed with the service desk team when the implications of what such a system might bring about was presented and how the work flow will be affected.
Description: B.SC.(HONS)BUS.&I.T.
URI: https://www.um.edu.mt/library/oar/handle/123456789/49285
Appears in Collections:Dissertations - FacEma - 2019
Dissertations - FacEMAMAn - 2019

Files in This Item:
File Description SizeFormat 
19BSCBIT004.pdf
  Restricted Access
1.13 MBAdobe PDFView/Open Request a copy


Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.