Gamified process-data cleaning

Overview

Despite the importance of data quality, it is often compromised. The majority of the time and energy in most data science projects is spent on data cleaning. Process-oriented data mining (process mining) is not an exception. A recent process mining survey shows that more than 60% of the time and effort is spent on data transformation and pre-processing. While, in most cases, the engagement of domain experts is required for accurate data cleaning, it is challenging to engage them in this task because it is tedious by nature.

Gamification is the use of game elements in non-gaming contexts to enhance user experience and engagement. It has the potential to address the challenge of domain expert engagement in the cleaning process-data (i.e., event logs). This project will look at gamifying the detection and repair of event log quality issues.

A preliminary work on this topic has been published: Sadeghianasl, S. Hofstede, A.H.M, Suriadi, S. Turkay, S.: Collaborative and Interactive Detection and Repair of Activity Labels in Process Event Logs, International Conference on Process Mining (ICPM), Padua, Italy, 2020, pp. 41-48.

Research engagement

This project may involve:

• a review of the state of the art in gamification, data cleaning, event log quality improvement, and the correlation between these topics.
• developing gamified techniques to detect and repair data quality issues in event logs
• developing methodologies for the design of data cleaning games
• communicating the findings in publications.

Outcomes

The prospective outcomes depend on the scope of the project and may include:

• literature review
• design and development of a prototype for gamified data cleaning
• identification of the most promising motivations and game elements to improve user experience in data cleaning
• development of methodologies for the design of data cleaning games.

Skills and experience

This project needs one or more of the following skills:

• preliminary knowledge of process mining and event logs
• programming standalone or web-based applications
• time management skills to deliver outcomes within a specific time frame
• excellent written and verbal communication skills

Start date

15 December, 2024

End date

28 February, 2025

Location

GP Campus, Y Block

Additional information

You may be eligible to apply for a research scholarship.

Keywords

• data science
• process science
• gamification
• data cleaning
• user behaviour

Contact

Contact the supervisor for more information.