Driven by ongoing improvements in machine learning, chatbots have increasingly grown from experimental interface prototypes to reliable and robust tools for process automation. Building on these advances, companies have identified various application scenarios, where the automated processing of human language can help foster task efficiency. To this end, the use of chatbots may not only decrease costs, but it is also said to boost user satisfaction. People's intention to use and/or reuse said technology, however, is often dependent on less utilitarian factors. Particularly trust and respective task satisfaction count as relevant usage predictors. In this paper, we thus present work that aims to shed some light on these two variable constructs. We report on an experimental study ($n=277$), investigating four different human-chatbot interaction tasks. After each task, participants were asked to complete survey items on perceived trust, perceived task complexity and perceived task satisfaction. Results show that task complexity impacts negatively on both trust and satisfaction. To this end, higher complexity was associated particularly with those conversations that relied on broad, descriptive chatbot answers, while conversations that span over several short steps were perceived less complex, even when the overall conversation was eventually longer.
相關內容
In the last decade, conversational search has attracted considerable attention. However, most research has focused on systems that can support a \emph{single} searcher. In this paper, we explore how systems can support \emph{multiple} searchers collaborating over an instant messaging platform (i.e., Slack). We present a ``Wizard of Oz'' study in which 27 participant pairs collaborated on three information-seeking tasks over Slack. Participants were unable to search on their own and had to gather information by interacting with a \emph{searchbot} directly from the Slack channel. The role of the searchbot was played by a reference librarian. Conversational search systems must be capable of engaging in \emph{mixed-initiative} interaction by taking and relinquishing control of the conversation to fulfill different objectives. Discourse analysis research suggests that conversational agents can take \emph{two} levels of initiative: dialog- and task-level initiative. Agents take dialog-level initiative to establish mutual belief between agents and task-level initiative to influence the goals of the other agents. During the study, participants were exposed to three experimental conditions in which the searchbot could take different levels of initiative: (1) no initiative, (2) only dialog-level initiative, and (3) both dialog- and task-level initiative. In this paper, we focus on understanding the Wizard's actions. Specifically, we focus on understanding the Wizard's motivations for taking initiative and their rationale for the timing of each intervention. To gain insights about the Wizard's actions, we conducted a stimulated recall interview with the Wizard. We present findings from a qualitative analysis of this interview data and discuss implications for designing conversational search systems to support collaborative search.
Human-machine interaction (HMI) and human-robot interaction (HRI) can assist structural monitoring and structural dynamics testing in the laboratory and field. In vibratory experimentation, one mode of generating vibration is to use electrodynamic exciters. Manual control is a common way of setting the input of the exciter by the operator. To measure the structural responses to these generated vibrations sensors are attached to the structure. These sensors can be deployed by repeatable robots with high endurance, which require on-the-fly control. If the interface between operators and the controls was augmented, then operators can visualize the experiments, exciter levels, and define robot input with a better awareness of the area of interest. Robots can provide better aid to humans if intelligent on-the-fly control of the robot is: (1) quantified and presented to the human; (2) conducted in real-time for human feedback informed by data. Information provided by the new interface would be used to change the control input based on their understanding of real-time parameters. This research proposes using Augmented Reality (AR) applications to provide humans with sensor feedback and control of actuators and robots. This method improves cognition by allowing the operator to maintain awareness of structures while adjusting conditions accordingly with the assistance of the new real-time interface. One interface application is developed to plot sensor data in addition to voltage, frequency, and duration controls for vibration generation. Two more applications are developed under similar framework, one to control the position of a mediating robot and one to control the frequency of the robot movement. This paper presents the proposed model for the new control loop and then compares the new approach with a traditional method by measuring time delay in control input and user efficiency.
The collection and use of personal data are becoming more common in today's data-driven culture. While there are many advantages to this, including better decision-making and service delivery, it also poses significant ethical issues around confidentiality and privacy. Text anonymisation tries to prune and/or mask identifiable information from a text while keeping the remaining content intact to alleviate privacy concerns. Text anonymisation is especially important in industries like healthcare, law, as well as research, where sensitive and personal information is collected, processed, and exchanged under high legal and ethical standards. Although text anonymization is widely adopted in practice, it continues to face considerable challenges. The most significant challenge is striking a balance between removing information to protect individuals' privacy while maintaining the text's usability for future purposes. The question is whether these anonymisation methods sufficiently reduce the risk of re-identification, in which an individual can be identified based on the remaining information in the text. In this work, we challenge the effectiveness of these methods and how we perceive identifiers. We assess the efficacy of these methods against the elephant in the room, the use of AI over big data. While most of the research is focused on identifying and removing personal information, there is limited discussion on whether the remaining information is sufficient to deanonymise individuals and, more precisely, who can do it. To this end, we conduct an experiment using GPT over anonymised texts of famous people to determine whether such trained networks can deanonymise them. The latter allows us to revise these methods and introduce a novel methodology that employs Large Language Models to improve the anonymity of texts.
Exoskeletons and orthoses are wearable mobile systems providing mechanical benefits to the users. Despite significant improvements in the last decades, the technology is not fully mature to be adopted for strenuous and non-programmed tasks. To accommodate this insufficiency, different aspects of this technology need to be analysed and improved. Numerous studies have tried to address some aspects of exoskeletons, e.g. mechanism design, intent prediction, and control scheme. However, most works have focused on a specific element of design or application without providing a comprehensive review framework. This study aims to analyse and survey the contributing aspects to this technology's improvement and broad adoption. To address this, after introducing assistive devices and exoskeletons, the main design criteria will be investigated from both physical Human-Robot Interaction (HRI) perspectives. In order to establish an intelligent HRI strategy and enable intuitive control for users, cognitive HRI will be investigated after a brief introduction to various approaches to their control strategies. The study will be further developed by outlining several examples of known assistive devices in different categories. And some guidelines for exoskeleton selection and possible mitigation of current limitations will be discussed.
In recent years, industry leaders and researchers have proposed to use technical provenance standards to address visual misinformation spread through digitally altered media. By adding immutable and secure provenance information such as authorship and edit date to media metadata, social media users could potentially better assess the validity of the media they encounter. However, it is unclear how end users would respond to provenance information, or how to best design provenance indicators to be understandable to laypeople. We conducted an online experiment with 595 participants from the US and UK to investigate how provenance information altered users' accuracy perceptions and trust in visual content shared on social media. We found that provenance information often lowered trust and caused users to doubt deceptive media, particularly when it revealed that the media was composited. We additionally tested conditions where the provenance information itself was shown to be incomplete or invalid, and found that these states have a significant impact on participants' accuracy perceptions and trust in media, leading them, in some cases, to disbelieve honest media. Our findings show that provenance, although enlightening, is still not a concept well-understood by users, who confuse media credibility with the orthogonal (albeit related) concept of provenance credibility. We discuss how design choices may contribute to provenance (mis)understanding, and conclude with implications for usable provenance systems, including clearer interfaces and user education.
Computing is a critical driving force in the development of human civilization. In recent years, we have witnessed the emergence of intelligent computing, a new computing paradigm that is reshaping traditional computing and promoting digital revolution in the era of big data, artificial intelligence and internet-of-things with new computing theories, architectures, methods, systems, and applications. Intelligent computing has greatly broadened the scope of computing, extending it from traditional computing on data to increasingly diverse computing paradigms such as perceptual intelligence, cognitive intelligence, autonomous intelligence, and human-computer fusion intelligence. Intelligence and computing have undergone paths of different evolution and development for a long time but have become increasingly intertwined in recent years: intelligent computing is not only intelligence-oriented but also intelligence-driven. Such cross-fertilization has prompted the emergence and rapid advancement of intelligent computing. Intelligent computing is still in its infancy and an abundance of innovations in the theories, systems, and applications of intelligent computing are expected to occur soon. We present the first comprehensive survey of literature on intelligent computing, covering its theory fundamentals, the technological fusion of intelligence and computing, important applications, challenges, and future perspectives. We believe that this survey is highly timely and will provide a comprehensive reference and cast valuable insights into intelligent computing for academic and industrial researchers and practitioners.
Trust has emerged as a key factor in people's interactions with AI-infused systems. Yet, little is known about what models of trust have been used and for what systems: robots, virtual characters, smart vehicles, decision aids, or others. Moreover, there is yet no known standard approach to measuring trust in AI. This scoping review maps out the state of affairs on trust in human-AI interaction (HAII) from the perspectives of models, measures, and methods. Findings suggest that trust is an important and multi-faceted topic of study within HAII contexts. However, most work is under-theorized and under-reported, generally not using established trust models and missing details about methods, especially Wizard of Oz. We offer several targets for systematic review work as well as a research agenda for combining the strengths and addressing the weaknesses of the current literature.
Recommender systems exploit interaction history to estimate user preference, having been heavily used in a wide range of industry applications. However, static recommendation models are difficult to answer two important questions well due to inherent shortcomings: (a) What exactly does a user like? (b) Why does a user like an item? The shortcomings are due to the way that static models learn user preference, i.e., without explicit instructions and active feedback from users. The recent rise of conversational recommender systems (CRSs) changes this situation fundamentally. In a CRS, users and the system can dynamically communicate through natural language interactions, which provide unprecedented opportunities to explicitly obtain the exact preference of users. Considerable efforts, spread across disparate settings and applications, have been put into developing CRSs. Existing models, technologies, and evaluation methods for CRSs are far from mature. In this paper, we provide a systematic review of the techniques used in current CRSs. We summarize the key challenges of developing CRSs into five directions: (1) Question-based user preference elicitation. (2) Multi-turn conversational recommendation strategies. (3) Dialogue understanding and generation. (4) Exploitation-exploration trade-offs. (5) Evaluation and user simulation. These research directions involve multiple research fields like information retrieval (IR), natural language processing (NLP), and human-computer interaction (HCI). Based on these research directions, we discuss some future challenges and opportunities. We provide a road map for researchers from multiple communities to get started in this area. We hope this survey helps to identify and address challenges in CRSs and inspire future research.
Machine learning plays a role in many deployed decision systems, often in ways that are difficult or impossible to understand by human stakeholders. Explaining, in a human-understandable way, the relationship between the input and output of machine learning models is essential to the development of trustworthy machine-learning-based systems. A burgeoning body of research seeks to define the goals and methods of explainability in machine learning. In this paper, we seek to review and categorize research on counterfactual explanations, a specific class of explanation that provides a link between what could have happened had input to a model been changed in a particular way. Modern approaches to counterfactual explainability in machine learning draw connections to the established legal doctrine in many countries, making them appealing to fielded systems in high-impact areas such as finance and healthcare. Thus, we design a rubric with desirable properties of counterfactual explanation algorithms and comprehensively evaluate all currently-proposed algorithms against that rubric. Our rubric provides easy comparison and comprehension of the advantages and disadvantages of different approaches and serves as an introduction to major research themes in this field. We also identify gaps and discuss promising research directions in the space of counterfactual explainability.
To address the sparsity and cold start problem of collaborative filtering, researchers usually make use of side information, such as social networks or item attributes, to improve recommendation performance. This paper considers the knowledge graph as the source of side information. To address the limitations of existing embedding-based and path-based methods for knowledge-graph-aware recommendation, we propose Ripple Network, an end-to-end framework that naturally incorporates the knowledge graph into recommender systems. Similar to actual ripples propagating on the surface of water, Ripple Network stimulates the propagation of user preferences over the set of knowledge entities by automatically and iteratively extending a user's potential interests along links in the knowledge graph. The multiple "ripples" activated by a user's historically clicked items are thus superposed to form the preference distribution of the user with respect to a candidate item, which could be used for predicting the final clicking probability. Through extensive experiments on real-world datasets, we demonstrate that Ripple Network achieves substantial gains in a variety of scenarios, including movie, book and news recommendation, over several state-of-the-art baselines.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191