Data Mining - Concepts and Techniques.

Explanation in artificial intelligence: Insights from the social sciences

What Video Games Have to Teach Us about Learning and Literacy

At the dawn of the fourth industrial revolution, we are witnessing a fast and widespread adoption of artificial intelligence (AI) in our daily life, which contributes to accelerating the shift towards a more algorithmic society. However, even with such unprecedented advancements, a key impediment to the use of AI-based systems is that they often lack transparency. Indeed, the black-box nature of these systems allows powerful predictions, but it cannot be directly explained. This issue has triggered a new debate on explainable AI (XAI). A research field holds substantial promise for improving trust and transparency of AI-based systems. It is recognized as the sine qua non for AI to continue making steady progress without disruption. This survey provides an entry point for interested researchers and practitioners to learn key aspects of the young and rapidly growing body of research related to XAI. Through the lens of the literature, we review the existing approaches regarding the topic, discuss trends surrounding its sphere, and present major research trajectories.

Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)

The Object Management Group's (OMG) Model Driven Architecture (MDA) strategy envisages a world where models play a more direct role in software production, being amenable to manipulation and transformation by machine. Model Driven Engineering (MDE) is wider in scope than MDA. MDE combines process and analysis with architecture. This article sets out a framework for model driven engineering, which can be used as a point of reference for activity in this area. It proposes an organisation of the modelling 'space' and how to locate models in that space. It discusses different kinds of mappings between models. It explains why process and architecture are tightly connected. It discusses the importance and nature of tools. It identifies the need for defining families of languages and transformations, and for developing techniques for generating/configuring tools from such definitions. It concludes with a call to align metamodelling with formal language engineering techniques.

Model Driven Engineering

Research is emerging on how end users can correct mistakes their intelligent agents make, but before users can correctly “debug” an intelligent agent, they need some degree of understanding of how it works. In this paper we consider ways intelligent agents should explain themselves to end users, especially focusing on how the soundness and completeness of the explanations impacts the fidelity of end users' mental models. Our findings suggest that completeness is more important than soundness: increasing completeness via certain information types helped participants' mental models and, surprisingly, their perception of the cost/benefit tradeoff of attending to the explanations. We also found that oversimplification, as per many commercial agents, can be a problem: when soundness was very low, participants experienced more mental demand and lost trust in the explanations, thereby reducing the likelihood that users will pay attention to such explanations at all.

/pdf/too-much-too-little-or-just-right-ways-explanations-impact-3slm7b6zya.pdf

Too much, too little, or just right? Ways explanations impact end users' mental models

Global software teams face challenges when collaborating over long distances, such as communicating changes in the project. During a four-month case study at IBM Ottawa Software Lab we observed the collaboration patterns of a multi-site development project team. In this period, we inspected project documentation, interviewed team leaders, attended project meetings, and spoke with developers to identify problems originated by the lack of awareness of changes related to the implementation of work items. Our observations show (1) that organizational culture has an effect on how developers are made aware; (2) that communication-based social networks revolving around particular work items are dynamic throughout development, and therefore awareness needs to be maintained in infrastructures of work; and (3) that information overload and communication breakdowns contributed to the generation of a broken integration build. We discuss these breakdowns in communication and implications for the design of collaboration tools that could mitigate these problems.

/pdf/awareness-in-the-wild-why-communication-breakdowns-occur-432hmoyq0f.pdf

Awareness in the Wild: Why Communication Breakdowns Occur

What does a user need to know to productively work with an intelligent agent? Intelligent agents and recommender systems are gaining widespread use, potentially creating a need for end users to understand how these systems operate in order to fix their agent's personalized behavior. This paper explores the effects of mental model soundness on such personalization by providing structural knowledge of a music recommender system in an empirical study. Our findings show that participants were able to quickly build sound mental models of the recommender system's reasoning, and that participants who most improved their mental models during the study were significantly more likely to make the recommender operate to their satisfaction. These results suggest that by helping end users understand a system's reasoning, intelligent agents may elicit more and better feedback, thus more closely aligning their output with each user's intentions.

/pdf/tell-me-more-the-effects-of-mental-model-soundness-on-3l4tut67wp.pdf

Tell me more?: the effects of mental model soundness on personalizing an intelligent agent

GenderMag: A Method for Evaluating Software's Gender Inclusiveness

Socio-technical congruence is an approach that measures coordination by examining the alignment between the technical dependencies and the social coordination in the project. We conduct a case study of coordination in the IBM Rational Team Concert project, which consists of 151 developers over seven geographically distributed sites, and expect that high congruence leads to a high probability of successful builds. We examine this relationship by applying two congruence measurements: an unweighted congruence measure from previous literature, and a weighted measure that overcomes limitations of the existing measure. We discover that there is a relationship between socio-technical congruence and build success probability, but only for certain build types, and observe that in some situations, higher congruence actually leads to lower build success rates. We also observe that a large proportion of zero-congruence builds are successful, and that socio-technical gaps in successful builds are larger than gaps in failed builds. Analysis of the social and technical aspects in IBM Rational Team Concert allows us to discuss the effects of congruence on build success. Our findings provide implications with respect to the limits of applicability of socio-technical congruence and suggest further improvements of socio-technical congruence to study coordination.

Irwin Kwan

Papers

Too much, too little, or just right? Ways explanations impact end users' mental models

Awareness in the Wild: Why Communication Breakdowns Occur

Tell me more?: the effects of mental model soundness on personalizing an intelligent agent

GenderMag: A Method for Evaluating Software's Gender Inclusiveness

Does Socio-Technical Congruence Have an Effect on Software Build Success? A Study of Coordination in a Software Project