Loughborough University
Browse
Alok Text_Mining_CII.pdf (303.39 kB)

The needs and benefits of Text Mining applications on Post-Project Reviews

Download (303.39 kB)
journal contribution
posted on 2009-11-25, 16:24 authored by Alok ChoudharyAlok Choudhary, Paul Oluikpe, Jennifer HardingJennifer Harding, Patricia CarrilloPatricia Carrillo
Post Project Reviews (PPRs) are a rich source of knowledge and data for organisations - if organisations have the time and resources to analyse them. Too often these reports are stored, unread by many who could benefit from them. PPR reports attempt to document the project experience – both good and bad. If these reports were analysed collectively, they may expose important detail, e.g. recurring problems or examples of good practice, perhaps repeated across a number of projects. However, because most companies do not have the resources to thoroughly examine PPR reports, either individually or collectively, important insights and opportunities to learn from previous projects, are missed. This research explores the application of knowledge discovery techniques and text mining to uncover patterns, associations, and trends from PPR reports. The results might then be used to address problem areas, enhance processes, and improve customer relationships. A case study related to two construction companies is presented in this paper and knowledge discovery techniques are used to analyze 50 PPR reports collected during the last three years. The case study has been examined in six contexts and the results show that Text Mining has a good potential to improve overall knowledge reuse and exploitation.

History

School

  • Mechanical, Electrical and Manufacturing Engineering

Citation

CHOUDHARY, A.K. ... et al, 2009. The needs and benefits of Text Mining applications on Post-Project Reviews. Computers in Industry, 60 (9), pp. 728-740.

Publisher

© Elsevier

Version

  • AM (Accepted Manuscript)

Publication date

2009

Notes

This article was published in the journal, Computers in Industry [© Elsevier]. The definitive version is available at: www.elsevier.com/locate/compind

ISSN

0166-3615

Language

  • en