Predicting the Attitudes of Opinion Holders (Leaders)
No Thumbnail Available
Authors
Author (Corporation)
Publication date
2016
Typ of student thesis
Master
Course of study
Collections
Type
11 - Student thesis
Editors
Editor (Corporation)
Supervisor
Parent work
Special issue
DOI of the original publication
Link
Series
Series number
Volume
Issue / Number
Pages / Duration
Patent number
Publisher / Publishing institution
Hochschule für Wirtschaft FHNW
Place of publication / Event location
Olten
Edition
Version
Programming language
Assignee
Practice partner / Client
Abstract
The purpose of this study is to provide a solution to predict the stance of opinion holders regarding certain issue statements that they already expressed in publicly available sources.In the political environment, experts forecast parties' positions on certain policy issues. This process is also known as 'coding'. The resulting forecasts of the codings are needed for web-based Voting Advice Applications (VAAs), where users can compare their political position with that of the different parties. Conducting these forecasts is expensive with regards to the experts required and time spent.This problem was investigated in this study by applying a design research methodology. In a rst phase, knowledge was gained about VAAs and the forecasting process of the political experts. On that basis, a prototype of a prediction software was built. This software was tested against real-world coding results from the United Kingdom parliamentary elections of 2015. The software is able to predict the stance of political parties with an accuracy of 52%. Besides its prediction accuracy, the software generates comprehensive reports with prediction details that contain valuable information for coders(such as justications for a party's stance). The prediction accuracy is rather low and will not provide reliable forecasts. On the other hand, the reports offer according to a coding expert advantages in terms of process improvements for coders. However, this statement could not be proved quantitatively. Through further analysis, several opportunities for future research were identified.
Keywords
Subject (DDC)
330 - Wirtschaft
Event
Exhibition start date
Exhibition end date
Conference start date
Conference end date
Date of the last check
ISBN
ISSN
Language
English
Created during FHNW affiliation
Yes
Strategic action fields FHNW
Publication status
Review
Open access category
License
Citation
STUBER, Thomas, 2016. Predicting the Attitudes of Opinion Holders (Leaders). Olten: Hochschule für Wirtschaft FHNW. Verfügbar unter: https://irf.fhnw.ch/handle/11654/39877