Engaging end-user driven recommender systems: personalization through web augmentation
- PDF / 4,962,873 Bytes
- 25 Pages / 439.642 x 666.49 pts Page_size
- 110 Downloads / 224 Views
Engaging end-user driven recommender systems: personalization through web augmentation Martin Wischenbart1 · Sergio Firmenich2,3 Gabriela Bosetti2 · Elisabeth Kapsammer4
· Gustavo Rossi2,3
·
Received: 30 November 2019 / Revised: 21 August 2020 / Accepted: 2 September 2020 / © The Author(s) 2020
Abstract In the past decades recommender systems have become a powerful tool to improve personalization on the Web. Yet, many popular websites lack such functionality, its implementation usually requires certain technical skills, and, above all, its introduction is beyond the scope and control of end-users. To alleviate these problems, this paper presents a novel tool to empower end-users without programming skills, without any involvement of website providers, to embed personalized recommendations of items into arbitrary websites on client-side. For this we have developed a generic meta-model to capture recommender system configuration parameters in general as well as in a web augmentation context. Thereupon, we have implemented a wizard in the form of an easy-to-use browser plugin, allowing the generation of so-called user scripts, which are executed in the browser to engage collaborative filtering functionality from a provided external REST service. We discuss functionality and limitations of the approach, and in a study with end-users we assess the usability and show its suitability for combining recommender systems with web augmentation techniques, aiming to empower end-users to implement controllable recommender applications for a more personalized browsing experience. Keywords Web augmentation · Visual programming · Client-side personalization · End-user programming · End-user development · Controllability of recommender systems · Browser-side trans-coding
1 Introduction Nowadays recommender systems are a popular means for personalizing user experience and services on the Web. They have a long-standing history in various domains and they are employed by a multitude of websites in areas such as e-commerce, movie databases,
Martin Wischenbart
[email protected]
Extended author information available on the last page of the article.
Multimedia Tools and Applications
Fig. 1 Adapted cocktailscout.de website with the random recipe shown by default (left menu bar, heading “Zufallsrezept”) and the additionally augmented personalized recipe recommendations (right menu bar, heading “Recommendations”). The augmented content blends in with the site’s style and the remainder of the right menu bar’s content is just shifted further below [38]
food recipes, or music streaming. In spite of their potential, however, beyond well-known or commercial websites oftentimes recommendation services are not implemented by site providers, perhaps for missing financial incentives. As an example, cocktailscout.de, once one of the largest German language websites for cocktail recipes,1 although it has a rating mechanism that is used for ranking of recipes, the site used to only provide a random recipe link on each page instead of
Data Loading...
