Advances in artificial intelligence, sensors and big data management have far-reaching societal impacts. As these systems augment our everyday lives, it becomes increasing-ly important for people to understand them and remain in control. We investigate how HCI researchers can help to develop accountable systems by performing a literature analysis of 289 core papers on explanations and explaina-ble systems, as well as 12,412 citing papers. Using topic modeling, co-occurrence and network analysis, we mapped the research space from diverse domains, such as algorith-mic accountability, interpretable machine learning, context-awareness, cognitive psychology, and software learnability. We reveal fading and burgeoning trends in explainable systems, and identify domains that are closely connected or mostly isolated. The time is ripe for the HCI community to ensure that the powerful new autonomous systems have intelligible interfaces built-in. From our results, we propose several implications and directions for future research to-wards this goal.

https://dl.acm.org/doi/pdf/10.1145/3173574.3174156

Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda

Increasingly, management researchers are using topic modeling, a new method borrowed from computer science, to reveal phenomenon-based constructs and grounded conceptual relationships in textual da...

/pdf/topic-modeling-in-management-research-rendering-new-theory-32xxxvydh7.pdf

Topic Modeling in Management Research: Rendering New Theory from Textual Data

We have recently seen many successful applications of recurrent neural networks (RNNs) on electronic medical records (EMRs), which contain histories of patients' diagnoses, medications, and other various events, in order to predict the current and future states of patients. Despite the strong performance of RNNs, it is often challenging for users to understand why the model makes a particular prediction. Such black-box nature of RNNs can impede its wide adoption in clinical practice. Furthermore, we have no established methods to interactively leverage users' domain expertise and prior knowledge as inputs for steering the model. Therefore, our design study aims to provide a visual analytics solution to increase interpretability and interactivity of RNNs via a joint effort of medical experts, artificial intelligence scientists, and visual analytics researchers. Following the iterative design process between the experts, we design, implement, and evaluate a visual analytics tool called RetainVis, which couples a newly improved, interpretable, and interactive RNN-based model called RetainEX and visualizations for users' exploration of EMR data in the context of prediction tasks. Our study shows the effective use of RetainVis for gaining insights into how individual medical codes contribute to making risk predictions, using EMRs of patients with heart failure and cataract symptoms. Our study also demonstrates how we made substantial changes to the state-of-the-art RNN model called RETAIN in order to make use of temporal information and increase interactivity. This study will provide a useful guideline for researchers that aim to design an interpretable and interactive visual analytics tool for RNNs.

RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records

How can a single person understand what’s going on in a collection of millions of documents? This is an increasingly widespread problem: sifting through an organization’s e-mails, understanding a decade worth of newspapers, or characterizing a scientific field’s research. This monograph explores the ways that humans and computers make sense of document collections through tools called topic models. Topic models are a statistical framework that help users understand large document collections; not just to find individual documents but to understand the general themes present in the collection. Applications of Topic Models describes the recent academic and industrial applications of topic models. In addition to topic models’ effective application to traditional problems like information retrieval, visualization, statistical inference, multilingual modeling, and linguistic understanding, Applications of Topic Models also reviews topic models’ ability to unlock large text collections for qualitative analysis. It reviews their successful use by researchers to help understand fiction, non-fiction, scientific publications, and political texts. Applications of Topic Models is aimed at the reader with some knowledge of document processing, basic understanding of some probability, and interested in many application domains. It discusses the information needs of each application area, and how those specific needs affect models, curation procedures, and interpretations. By the end of the monograph, it is hoped that readers will be excited enough to attempt to embark on building their own topic models. It should also be of interest to topic model experts as the coverage of diverse applications may expose models and approaches they had not seen before.

/pdf/applications-of-topic-models-vlav480we5.pdf

Applications of Topic Models

Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

Topic modeling is a common tool for understanding large bodies of text, but is typically provided as a “take it or leave it” proposition. Incorporating human knowledge in unsupervised learning is a promising approach to create high-quality topic models. Existing interactive systems and modeling algorithms support a wide range of refinement operations to express feedback. However, these systems’ interactions are primarily driven by algorithmic convenience, ignoring users who may lack expertise in topic modeling. To better understand how non-expert users understand, assess, and refine topics, we conducted two user studies—an in-person interview study and an online crowdsourced study. These studies demonstrate a disconnect between what non-expert users want and the complex, low-level operations that current interactive systems support. In particular, our findings include: (1) analysis of how non-expert users perceive topic models; (2) characterization of primary refinement operations expected by non-expert users and ordered by relative preference; (3) further evidence of the benefits of supporting users in directly refining a topic model; (4) design implications for future human-in-the-loop topic modeling interfaces.

/pdf/the-human-touch-how-non-expert-users-perceive-interpret-and-2b3cesrwnm.pdf

The human touch: How non-expert users perceive, interpret, and fix topic models

Human-in-the-loop topic modeling allows users to guide the creation of topic models and to improve model quality without having to be experts in topic modeling algorithms. Prior work in this area has focused either on algorithmic implementation without understanding how users actually wish to improve the model or on user needs but without the context of a fully interactive system. To address this disconnect, we implemented a set of model refinements requested by users in prior work and conducted a study with twelve non-expert participants to examine how end users are affected by issues that arise with a fully interactive, user-centered system. As these issues mirror those identified in interactive machine learning more broadly, such as unpredictability, latency, and trust, we also examined interactive machine learning challenges with non-expert end users through the lens of human-in-the-loop topic modeling. We found that although users experience unpredictability, their reactions vary from positive to negative, and, surprisingly, we did not find any cases of distrust, but instead noted instances where users perhaps trusted the system too much or had too little confidence in themselves.

https://dl.acm.org/doi/pdf/10.1145/3172944.3172965

Closing the Loop: User-Centered Design and Evaluation of a Human-in-the-Loop Topic Modeling System

Social media, particularly Twitter, provides an abundance of real-time data. To account for this volume, researchers often use automated analysis and visualization techniques to produce a high-level overview of a Twitter stream. Existing techniques for understanding Twitter data make use of hashtags or word-pairs and may ignore the complex trends in discussions over time. To remedy this, we present an application of statistical topic modeling and alignment (binned topic models) to group related tweets into automatically generated topics and TopicFlow, an interactive tool to visualize the evolution of these topics. The effectiveness of this visualization for reasoning about large data sets is demonstrated by a usability study with 18 participants.

TopicFlow: visualizing topic alignment of Twitter data over time

Existing algorithms for understanding large collections of documents often produce output that is nearly as difficult and time consuming to interpret as reading each of the documents themselves. Topic modeling is a text understanding algorithm that discovers the “topics” or themes within a collection of documents. Tools based on topic modeling become increasingly complex as the number of topics required to best represent the collection increases. In this work, we present Hiérarchie, an interactive visualization that adds structure to large topic models, making them approachable and useful to an end user. Additionally, we demonstrate Hiérarchie’s ability to analyze a diverse document set regarding a trending news topic.

Hiearchie: Visualization for Hierarchical Topic Models

Probabilistic topic models are important tools for indexing, summarizing, and analyzing large document collections by their themes.  However, promoting end-user understanding of topics remains an open research problem.  We compare labels generated by users given four topic visualization techniques—word lists, word lists with bars, word clouds, and network graphs—against each other and against automatically generated labels.  Our basis of comparison is participant ratings of how well labels describe documents from the topic. Our study has two phases: a labeling phase where participants label visualized topics and a validation phase where different participants select which labels best describe the topics' documents.  Although all visualizations produce similar quality labels, simple visualizations such as word lists allow participants to quickly understand topics, while complex visualizations take longer but expose multi-word expressions that simpler visualizations obscure.  Automatic labels lag behind user-created labels, but our dataset of manually labeled topics highlights linguistic patterns (e.g., hypernyms, phrases) that can be used to improve automatic topic labeling algorithms.

/pdf/evaluating-visual-representations-for-topic-understanding-3o82etv84o.pdf

Alison Smith

Papers

The human touch: How non-expert users perceive, interpret, and fix topic models

Closing the Loop: User-Centered Design and Evaluation of a Human-in-the-Loop Topic Modeling System

TopicFlow: visualizing topic alignment of Twitter data over time

Hiearchie: Visualization for Hierarchical Topic Models

Evaluating Visual Representations for Topic Understanding and Their Effects on Manually Generated Labels