Document Type

Conference Paper


Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence


1.2 COMPUTER AND INFORMATION SCIENCE, Computer Sciences, Information Science, Ethics

Publication Details

ICDS 2021: The 15th International Conference on Digital Society, Nice, France, 18th – 22nd, July 2021 (online)


In the theories of User Interfaces (UI) and User Experience (UX), the goal is generally to help understand the needs of users and how software can be best configured to optimize how the users can interact with it by removing any unnecessary barriers. However, some systems are designed to make people unwillingly agree to share more data than they intend to, or to spend more money than they plan to, using deception or other psychological nudges. User Interface experts have categorized a number of these tricks that are commonly used and have called them Dark Patterns. Dark Patterns are varied in their form and what they do, and the goal of this research is to design and develop a framework for automated detection of potential instances of web-based dark patterns. To achieve this we explore each of the many canonical dark patterns and identify whether or not it is technically possible to automatically detect that particular pattern. Some patterns are easier to detect than others, and there others that are impossible to detect in an automated fashion. For example, some patterns are straightforward and use confusing terminology to flummox the users, e.g. “Click here if you do not wish to opt out of our mailing list”, and these are reasonably simple to detect, whereas others, for example, sites that prevent users from doing a price comparison with similar products might not be readily detectable. This paper presents a framework to automatically detect dark patterns. We present and analyze known dark patterns in terms of whether they can be: (1) detected in an automated way (either partially or fully), (2) detected in a manual way (either partially or fully) and (3) cannot be detected at all. We present the results of our analysis and outline a proposed software tool to detect dark patterns on websites, social media platforms and mobile applications.