Mark Sanderson
YOU?
Author Swipe
View article: "Nuisance is Better Than Nothing?": Exploring How Pedestrians and Cyclists Perceive Automated E-Scooter Alerts in Shared Spaces MHCI023
"Nuisance is Better Than Nothing?": Exploring How Pedestrians and Cyclists Perceive Automated E-Scooter Alerts in Shared Spaces MHCI023 Open
Electric scooters (e-scooters) offer flexible urban mobility but raise safety concerns in shared spaces. This study investigates how e-scooters can better communicate their presence to pedestrians and cyclists in shared active mobility env…
View article: Diverse Negative Sampling for Implicit Collaborative Filtering
Diverse Negative Sampling for Implicit Collaborative Filtering Open
Implicit collaborative filtering recommenders are usually trained to learn user positive preferences. Negative sampling, which selects informative negative items to form negative training data, plays a crucial role in this process. Since i…
View article: Principles and Guidelines for the Use of LLM Judges
Principles and Guidelines for the Use of LLM Judges Open
Large Language Models (LLMs) are increasingly used to evaluate information retrieval (IR) systems, generating relevance judgments traditionally made by human assessors. Recent empirical studies suggest that LLM-based evaluations often alig…
View article: Demographically-Inspired Query Variants Using an LLM
Demographically-Inspired Query Variants Using an LLM Open
This study proposes a method to diversify queries in existing test collections to reflect some of the diversity of search engine users, aligning with an earlier vision of an 'ideal' test collection. A Large Language Model (LLM) is used to …
View article: Perfect counterfactuals in imperfect worlds: modelling noisy implementation of actions in sequential algorithmic recourse
Perfect counterfactuals in imperfect worlds: modelling noisy implementation of actions in sequential algorithmic recourse Open
Algorithmic recourse suggests actions to individuals who have been adversely affected by automated decision-making, helping them to achieve the desired outcome. Knowing the recourse, however, does not guarantee that users can implement it …
View article: Estimating Quantum Execution Requirements for Feature Selection in Recommender Systems Using Extreme Value Theory
Estimating Quantum Execution Requirements for Feature Selection in Recommender Systems Using Extreme Value Theory Open
Recent advances in quantum computing have significantly accelerated research into quantum-assisted information retrieval and recommender systems, particularly in solving feature selection problems by formulating them as Quadratic Unconstra…
View article: Dagstuhl Perspectives Workshop 24352 -- Conversational Agents: A Framework for Evaluation (CAFE): Manifesto
Dagstuhl Perspectives Workshop 24352 -- Conversational Agents: A Framework for Evaluation (CAFE): Manifesto Open
During the workshop, we deeply discussed what CONversational Information ACcess (CONIAC) is and its unique features, proposing a world model abstracting it, and defined the Conversational Agents Framework for Evaluation (CAFE) for the eval…
View article: Watch Out! E-scooter Coming Through!: Multimodal Sensing of Mixed Traffic Use and Conflicts Through Riders' Ego-centric Views
Watch Out! E-scooter Coming Through!: Multimodal Sensing of Mixed Traffic Use and Conflicts Through Riders' Ego-centric Views Open
E-scooters are becoming a popular means of urban transportation. However, this increased popularity brings challenges, such as road accidents and conflicts when sharing space with traditional transport modes. An in-depth understanding of e…
View article: Leveraging Complementary AI Explanations to Mitigate Misunderstanding in XAI
Leveraging Complementary AI Explanations to Mitigate Misunderstanding in XAI Open
Artificial intelligence explanations can make complex predictive models more comprehensible. To be effective, however, they should anticipate and mitigate possible misinterpretations, e.g., arising when users infer incorrect information th…
View article: Watch Out E-scooter Coming Through: Multimodal Sensing of Mixed Traffic Use and Conflicts Through Riders Ego-centric Views
Watch Out E-scooter Coming Through: Multimodal Sensing of Mixed Traffic Use and Conflicts Through Riders Ego-centric Views Open
E-scooters are becoming a popular means of urban transportation. However, this increased popularity brings challenges, such as road accidents and conflicts when sharing space with traditional transport modes. An in-depth understanding of e…
View article: LLMs can be Fooled into Labelling a Document as Relevant (best caf\'e near me; this paper is perfectly relevant)
LLMs can be Fooled into Labelling a Document as Relevant (best caf\'e near me; this paper is perfectly relevant) Open
LLMs are increasingly being used to assess the relevance of information objects. This work reports on experiments to study the labelling of short texts (i.e., passages) for relevance, using multiple open-source and proprietary LLMs. While …
View article: Metamorphic Evaluation of ChatGPT as a Recommender System
Metamorphic Evaluation of ChatGPT as a Recommender System Open
With the rise of Large Language Models (LLMs) such as ChatGPT, researchers have been working on how to utilize the LLMs for better recommendations. However, although LLMs exhibit black-box and probabilistic characteristics (meaning their i…
View article: Performance-Driven QUBO for Recommender Systems on Quantum Annealers
Performance-Driven QUBO for Recommender Systems on Quantum Annealers Open
We propose Counterfactual Analysis Quadratic Unconstrained Binary Optimization (CAQUBO) to solve QUBO problems for feature selection in recommender systems. CAQUBO leverages counterfactual analysis to measure the impact of individual featu…
View article: Explaining Recommendation Fairness from a User/Item Perspective
Explaining Recommendation Fairness from a User/Item Perspective Open
Recommender systems play a crucial role in personalizing user experiences, yet ensuring fairness in their outcomes remains an elusive challenge. This work explores the impact of individual users or items on the fairness of recommender syst…
View article: Perfect Counterfactuals in Imperfect Worlds: Modelling Noisy Implementation of Actions in Sequential Algorithmic Recourse
Perfect Counterfactuals in Imperfect Worlds: Modelling Noisy Implementation of Actions in Sequential Algorithmic Recourse Open
Algorithmic recourse suggests actions to individuals who have been adversely affected by automated decision-making, helping them to achieve the desired outcome. Knowing the recourse, however, does not guarantee that users can implement it …
View article: Online and Offline Evaluation in Search Clarification
Online and Offline Evaluation in Search Clarification Open
The effectiveness of clarification question models in engaging users within search systems is currently constrained, casting doubt on their overall usefulness. To improve the performance of these models, it is crucial to employ assessment …
View article: Uncontextualized significance considered dangerous
Uncontextualized significance considered dangerous Open
We examine the context of significance tests in offline retrieval experiments. Our Information Retrieval (IR) community is notable for its experimental rigour: the use of statistical significance is grows across our publications. However, …
View article: Temporal Conformity-aware Hawkes Graph Network for Recommendations
Temporal Conformity-aware Hawkes Graph Network for Recommendations Open
Many existing recommender systems (RSs) assume user behavior is governed solely by their interests. However, the peer effect often influences individual decision-making, which leads to conformity behavior. Conventional solutions that elimi…
View article: Generative Information Retrieval Evaluation
Generative Information Retrieval Evaluation Open
In this chapter, we consider generative information retrieval evaluation from two distinct but interrelated perspectives. First, large language models (LLMs) themselves are rapidly becoming tools for evaluation, with current research indic…
View article: Measuring the retrievability of digital library content using analytics data
Measuring the retrievability of digital library content using analytics data Open
Digital libraries aim to provide value to users by housing content that is accessible and searchable. Often such access is afforded through external web search engines. In this article, we measure how easily digital library content can be …
View article: Online and Offline Evaluation in Search Clarification
Online and Offline Evaluation in Search Clarification Open
The effectiveness of clarification question models in engaging users within search systems is currently constrained, casting doubt on their overall usefulness. To improve the performance of these models, it is crucial to employ assessment …
View article: How Crowd Worker Factors Influence Subjective Annotations: A Study of Tagging Misogynistic Hate Speech in Tweets
How Crowd Worker Factors Influence Subjective Annotations: A Study of Tagging Misogynistic Hate Speech in Tweets Open
Crowdsourced annotation is vital to both collecting labelled data to train and test automated content moderation systems and to support human-in-the-loop review of system decisions. However, annotation tasks such as judging hate speech are…
View article: Designing and Evaluating Presentation Strategies for Fact-Checked Content
Designing and Evaluating Presentation Strategies for Fact-Checked Content Open
With the rapid growth of online misinformation, it is crucial to have\nreliable fact-checking methods. Recent research on finding check-worthy claims\nand automated fact-checking have made significant advancements. However,\nlimited guidan…
View article: Comprehension Is a Double-Edged Sword: Over-Interpreting Unspecified Information in Intelligible Machine Learning Explanations
Comprehension Is a Double-Edged Sword: Over-Interpreting Unspecified Information in Intelligible Machine Learning Explanations Open
Automated decision-making systems are becoming increasingly ubiquitous, which creates an immediate need for their interpretability and explainability. However, it remains unclear whether users know what insights an explanation offers and, …