Despite the wide-spread use of multi-list or carousel (Netflix-like) interfaces in e-commerce and streaming services, there is little academic research (less than 30 papers), especially when compared to works for single-list interfaces. Recent eye tracking results [5] have shown that users browse multi-list and carousels significantly differently than other interfaces. Carousels are much more complex, allowing a wide-range of browsing/interaction sequences with multiple topic defined-lists that can be swiped to see more items. To account for this complexity and improve recommendations, recommender systems should be designed specifically for the interfaces they are used on, in other words interface-aware recommenders.

The unique capabilities of Large Language Models (LLMs), such as the natural language text generation ability, position them as strong candidates for providing explanation for recommendations. However, despite the size of the LLM, most existing models struggle to produce zero-shot explanations reliably. To address this issue, we propose a framework called Logic-Scaffolding, that combines the ideas of aspect-based explanation and chain-of-thought prompting to generate explanations through intermediate reasoning steps. In this paper, we share our experience in building the framework and present an interactive demonstration for exploring our results.

Offline data-driven evaluation is considered a low-cost and more accessible alternative to the online empirical method of assessing the quality of recommender systems. Despite their popularity and effectiveness, most data-driven approaches are unsuitable for evaluating interactive recommender systems. In this article, we attempt to address this issue by simulating the user interactions with the system as a part of the evaluation process. Particularly, we demonstrate that simulated users find their desired item more efficiently when recommendations are presented as a list of carousels compared to a simple ranked list.

Recommending online resources to patients with ovarian cancer and their caregivers is a challenging task. On one hand, the recommended items must be relevant, recent, and reliable. On the other hand, they need to match the user’s levels of disease-specific health literacy. In this demonstration, we describe the overall architecture and key components of HELPeR, a knowledge-adaptive interactive recommender system for ovarian cancer patients and their caregivers.

We present Grapevine, a user-controlled recommender that enables undergraduate and graduate students to find a suitable research advisor. This system combines the ideas from the areas of exploratory search, user modeling, and recommender systems by employing state-of-the-art knowledge extraction, grape-based recommendation, and an intelligent user interface. In this paper, we demonstrate the system’s key components and how they work as a whole.

Nowadays people share everything on online social networks, from daily life stories to the latest local and global news and events. Many researchers have exploited this as a source for understanding the user behaviour and profile in various settings. In this paper, we address the specific problem of user behavioural profiling in the context of cultural and artistic events. We propose a specific analysis pipeline that aims at examining the profile of online users, based on the textual content they published online. The pipeline covers the following aspects: data extraction and enrichment, topic modeling, user clustering, and prediction of interest. We show our approach at work for the monitoring of participation to a large-scale artistic installation that collected more than 1.5 million visitors in just two weeks (namely The Floating Piers , by Christo and Jeanne-Claude ). We report our findings and discuss the pros and cons of the work.