Extracting sentiment from healthcare survey data: An evaluation of sentiment analysis tools

Georgiou, Despo; MacFarlane, Andrew and Russell-Rose, Tony. 2015. 'Extracting sentiment from healthcare survey data: An evaluation of sentiment analysis tools'. In: 2015 Science and Information Conference (SAI). London, United Kingdom 28-30 July 2015. [Conference or Workshop Item]

[img]
Preview
Text
extracting-sentiment-from-healthcare-survey-data.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (806kB) | Preview

Abstract or Description

Sentiment analysis is an emerging discipline with many analytical tools available. This project aimed to examine a number of tools regarding their suitability for healthcare data. A comparison between commercial and non-commercial tools was made using responses from an online survey which evaluated design changes made to a clinical information service. The commercial tools were Semantria and TheySay and the noncommercial tools were WEKA and Google Prediction API. Different approaches were followed for each tool to determine the polarity of each response (i.e. positive, negative or neutral). Overall, the non-commercial tools outperformed their commercial counterparts. However, due to the different features offered by the tools, specific recommendations are made for each. In addition, single-sentence responses were tested in isolation to determine the extent to which they more clearly express a single polarity. Further work can be done to establish the relationship between single-sentence responses and the sentiment they express.

Item Type:

Conference or Workshop Item (Paper)

Identification Number (DOI):

https://doi.org/10.1109/SAI.2015.7237168

Departments, Centres and Research Units:

Computing

Dates:

DateEvent
28 July 2015Accepted
3 September 2015Published

Event Location:

London, United Kingdom

Date range:

28-30 July 2015

Item ID:

27119

Date Deposited:

10 Oct 2019 15:56

Last Modified:

09 Jun 2021 14:44

URI:

https://research.gold.ac.uk/id/eprint/27119

View statistics for this item...

Edit Record Edit Record (login required)