ACM Transactions on Interactive Intelligent Systems最新文献

Existing eXplainable Artificial Intelligence (XAI) techniques support people in interpreting AI advice. However, while previous work evaluates the users’ understanding of explanations, factors influencing the decision support are largely overlooked in the literature. This paper addresses this gap by studying the impact of user uncertainty, AI correctness, and the interaction between AI uncertainty and explanation logic-styles, for classification tasks. We conducted two separate studies: one requesting participants to recognise hand-written digits and one to classify the sentiment of reviews. To assess the decision making, we analysed the task performance, agreement with the AI suggestion, and the user’s reliance on the XAI interface elements. Participants make their decision relying on three pieces of information in the XAI interface (image or text instance, AI prediction, and explanation). Participants were shown one explanation style (between-participants design): according to three styles of logical reasoning (inductive, deductive, and abductive). This allowed us to study how different levels of AI uncertainty influence the effectiveness of different explanation styles. The results show that user uncertainty and AI correctness on predictions significantly affected users’ classification decisions considering the analysed metrics. In both domains (images and text), users relied mainly on the instance to decide. Users were usually overconfident about their choices, and this evidence was more pronounced for text. Furthermore, the inductive style explanations led to over-reliance on the AI advice in both domains – it was the most persuasive, even when the AI was incorrect. The abductive and deductive styles have complex effects depending on the domain and the AI uncertainty levels.

Adversarial attacks on a convolutional neural network (CNN)—injecting human-imperceptible perturbations into an input image—could fool a high-performance CNN into making incorrect predictions. The success of adversarial attacks raises serious concerns about the robustness of CNNs, and prevents them from being used in safety-critical applications, such as medical diagnosis and autonomous driving. Our work introduces a visual analytics approach to understanding adversarial attacks by answering two questions: (1) which neurons are more vulnerable to attacks and (2) which image features do these vulnerable neurons capture during the prediction?For the first question, we introduce multiple perturbation-based measures to break down the attacking magnitude into individual CNN neurons and rank the neurons by their vulnerability levels. For the second, we identify image features (e.g., cat ears) that highly stimulate a user-selected neuron to augment and validate the neuron’s responsibility. Furthermore, we support an interactive exploration of a large number of neurons by aiding with hierarchical clustering based on the neurons’ roles in the prediction. To this end, a visual analytics system is designed to incorporate visual reasoning for interpreting adversarial attacks. We validate the effectiveness of our system through multiple case studies as well as feedback from domain experts.

eXplainable AI (XAI) involves two intertwined but separate challenges: the development of techniques to extract explanations from black-box AI models, and the way such explanations are presented to users, i.e., the explanation user interface. Despite its importance, the second aspect has received limited attention so far in the literature. Effective AI explanation interfaces are fundamental for allowing human decision-makers to take advantage and oversee high-risk AI systems effectively. Following an iterative design approach, we present the first cycle of prototyping-testing-redesigning of an explainable AI technique, and its explanation user interface for clinical Decision Support Systems (DSS). We first present an XAI technique that meets the technical requirements of the healthcare domain: sequential, ontology-linked patient data, and multi-label classification tasks. We demonstrate its applicability to explain a clinical DSS, and we design a first prototype of an explanation user interface. Next, we test such a prototype with healthcare providers and collect their feedback, with a two-fold outcome: first, we obtain evidence that explanations increase users’ trust in the XAI system, and second, we obtain useful insights on the perceived deficiencies of their interaction with the system, so that we can re-design a better, more human-centered explanation interface.

Users’ personality traits can take an active role in affecting their behavior when they interact with a computer interface. However, in the area of recommender systems (RS), though personality-based RS has been extensively studied, most works focus on algorithm design, with little attention paid to studying whether and how the personality may influence users’ interaction with the recommendation interface. In this manuscript, we report the results of a user study (with 108 participants) that not only measured the influence of users’ personality traits on their perception and performance when using the recommendation interface but also employed an eye-tracker to in-depth reveal how personality may influence users’ eye-movement behavior. Moreover, being different from related work that has mainly been conducted in a single product domain, our user study was performed in three typical application domains (i.e., electronics like smartphones, entertainment like movies, and tourism like hotels). Our results show that mainly three personality traits, i.e., Openness to experience, Conscientiousness, and Agreeableness, significantly influence users’ perception and eye-movement behavior, but the exact influences vary across the domains. Finally, we provide a set of guidelines that might be constructive for designing a more effective recommendation interface based on user personality.

Using computational notebooks (e.g., Jupyter Notebook), data scientists rationalize their exploratory data analysis (EDA) based on their prior experience and external knowledge, such as online examples. For novices or data scientists who lack specific knowledge about the dataset or problem to investigate, effectively obtaining and understanding the external information is critical to carrying out EDA. This article presents EDAssistant, a JupyterLab extension that supports EDA with in situ search of example notebooks and recommendation of useful APIs, powered by novel interactive visualization of search results. The code search and recommendation are enabled by advanced machine learning models, trained on a large corpus of EDA notebooks collected online. A user study is conducted to investigate both EDAssistant and data scientists’ current practice (i.e., using external search engines). The results demonstrate the effectiveness and usefulness of EDAssistant, and participants appreciated its smooth and in-context support of EDA. We also report several design implications regarding code recommendation tools.

The emergence of the micro-moment concept highlights the influence of context; recommender system design should reflect this trend. In response to different contexts, a micro-moment recommender system (MMRS) requires an effective interaction mechanism that allows users to easily interact with the system in a way that supports autonomy and promotes the creation and expression of self. We study four types of interaction mechanisms to understand which personalization approach is the most suitable design for MMRSs. We assume that designs that support micro-moment needs well are those that give users more control over the system and constitute a lighter user burden. We test our hypothesis via a two-week between-subject field study in which participants used our system and provided feedback. User-initiated and mix-initiated intention mechanisms show higher perceived active control, and the additional controls do not add to user burdens. Therefore, these two designs suit the MMRS interaction mechanism.

Image and video data analysis has become an increasingly important research area with applications in different domains such as security surveillance, healthcare, augmented and virtual reality, video and image editing, activity analysis and recognition, synthetic content generation, distance education, telepresence, remote sensing, sports analytics, art, non-photorealistic rendering, search engines, and social media. Recent advances in Artificial Intelligence (AI) and particularly deep learning have sparked new research challenges and led to significant advancements, especially in image and video analysis. These advancements have also resulted in significant research and development in other areas such as visualization and visual analytics, and have created new opportunities for future lines of research. In this survey article, we present the current state of the art at the intersection of visualization and visual analytics, and image and video data analysis. We categorize the visualization articles included in our survey based on different taxonomies used in visualization and visual analytics research. We review these articles in terms of task requirements, tools, datasets, and application areas. We also discuss insights based on our survey results, trends and patterns, the current focus of visualization research, and opportunities for future research.

We developed a method to synthesize game levels that accounts for the degree of collaboration required by two players to finish a given game level. We first asked a game level designer to create playable game level chunks. Then, two artificial intelligence (AI) virtual agents driven by behavior trees played each game level chunk. We recorded the degree of collaboration required to accomplish each game level chunk by the AI virtual agents and used it to characterize each game level chunk. To synthesize a game level, we assigned to the total cost function cost terms that encode both the degree of collaboration and game level design decisions. Then, we used a Markov-chain Monte Carlo optimization method, called simulated annealing, to solve the total cost function and proposed a design for a game level. We synthesized three game levels (low, medium, and high degrees of collaboration game levels) to evaluate our implementation. We then recruited groups of participants to play the game levels to explore whether they would experience a certain degree of collaboration and validate whether the AI virtual agents provided sufficient data that described the collaborative behavior of players in each game level chunk. By collecting both in-game objective measurements and self-reported subjective ratings, we found that the three game levels indeed impacted the collaboration gameplay behavior of our participants. Moreover, by analyzing our collected data, we found moderate and strong correlations between the participants and the AI virtual agents. These results show that game developers can consider AI virtual agents as an alternative method for evaluating the degree of collaboration required to finish a game level.