University of Twente Student Theses

Login

Idea Quality Classification in Ideation Contests : Leveraging Textual and Non-Textual Features with Machine Learning

Kluit, D.R. (2023) Idea Quality Classification in Ideation Contests : Leveraging Textual and Non-Textual Features with Machine Learning.

[img] PDF
1MB
Abstract:This research paper investigates the evaluation of idea quality in innovation contests using a machine learning approach. The study aims to explore the factors contributing to higher ranked ideas by equating idea quality with performance in such contests. It examines the role of machine learning models in evaluating idea quality and compares their performance to a baseline no information rate. As the dataset size increases, the cross-validated machine learning models approach statistical significance. The research identifies several factors that significantly impact the performance of machine learning models. These include team size, the level of elaboration in the idea challenge and solution, and the readability of the idea itself. The study also delves into the influence of feedback quality on idea quality, specifically analysing the relationship between feedback sources' expertise and the idea topic. It suggests that diverse expertise among coaches positively impacts the perceived quality of ideas. This paper offers a valuable framework for assessing idea quality based on contest rankings. The insights gained from team size, idea elaboration, and feedback expertise provide practical guidance for participants and organisers to enhance idea quality and maximize the benefits of innovation contests.
Item Type:Essay (Master)
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:85 business administration, organizational science
Programme:Business Administration MSc (60644)
Link to this item:https://purl.utwente.nl/essays/95593
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page