Story and Discourse. Narrative Structure in Fiction and Film

Visual analytics for machine learning has recently evolved as one of the most exciting areas in the field of visualization. To better identify which research topics are promising and to learn how to apply relevant techniques in visual analytics, we systematically review 259 papers published in the last ten years together with representative works before 2010. We build a taxonomy, which includes three first-level categories: techniques before model building, techniques during modeling building, and techniques after model building. Each category is further characterized by representative analysis tasks, and each task is exemplified by a set of recent influential works. We also discuss and highlight research challenges and promising potential future research opportunities useful for visual analytics researchers.

/pdf/a-survey-of-visual-analytics-techniques-for-machine-learning-up38fctryh.pdf

A survey of visual analytics techniques for machine learning

Machine learning (ML) models are nowadays used in complex applications in various domains such as medicine, bioinformatics, and other sciences. Due to their black box nature, however, it may someti ...

The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations

Sémiologie Graphique: les diagrammes, les réseaux, les cartes@@@Semiologie Graphique: les diagrammes, les reseaux, les cartes

Adversarial examples, generated by adding small but intentionally imperceptible perturbations to normal examples, can mislead deep neural networks (DNNs) to make incorrect predictions. Although much work has been done on both adversarial attack and defense, a fine-grained understanding of adversarial examples is still lacking. To address this issue, we present a visual analysis method to explain why adversarial examples are misclassified. The key is to compare and analyze the datapaths of both the adversarial and normal examples. A datapath is a group of critical neurons along with their connections. We formulate the datapath extraction as a subset selection problem and solve it by constructing and training a neural network. A multi-level visualization consisting of a network-level visualization of data flows, a layer-level visualization of feature maps, and a neuron-level visualization of learned features, has been designed to help investigate how datapaths of adversarial and normal examples diverge and merge in the prediction process. A quantitative evaluation and a case study were conducted to demonstrate the promise of our method to explain the misclassification of adversarial examples.

Analyzing the Noise Robustness of Deep Neural Networks

Archive-It, a subscription service from the Internet Archive, allows users to create, maintain and view digital collections of web resources. The current interface of Archive-It is largely text-based, supporting drill-down navigation using lists of URIs. To provide an overview of each collection and highlight the collection's underlying characteristics, we present four alternate visualizations (image plot with histogram, wordle, bubble chart and timeline). The sites in an Archive-It collection may be organized by the collection curator into groups for easier navigation. However, many collections do not have such groupings, making them difficult to explore. We introduce a heuristics-based categorization for such collections.

/pdf/visualizing-digital-collections-at-archive-it-334ezei5z2.pdf

Visualizing digital collections at archive-it

A system for generating storyline visualizations using hierarchical task network planning

Training data for training a neural network usable for electronic sentiment analysis can be automatically constructed. For example, an electronic communication usable for training the neural network and including multiple characters can be received. A sentiment dictionary including multiple expressions mapped to multiple sentiment values representing different sentiments can be received. Each expression in the sentiment dictionary can be mapped to a corresponding sentiment value. An overall sentiment for the electronic communication can be determined using the sentiment dictionary. Training data usable for training the neural network can be automatically constructed based on the overall sentiment of the electronic communication. The neural network can be trained using the training data. A second electronic communication including an unknown sentiment can be received. At least one sentiment associated with the second electronic communication can be determined using the neural network.

Automatically constructing training sets for electronic sentiment analysis

Deep neural networks (DNNs) have made tremendous progress in many different areas in recent years. How these networks function internally, however, is often not well understood. Advances in under-standing DNNs will benefit and accelerate the development of the field. We present TNNVis, a visualization system that supports un-derstanding of deep neural networks specifically designed to analyze text. TNNVis focuses on DNNs composed of fully connected and convolutional layers. It integrates visual encodings and interaction techniques chosen specifically for our tasks. The tool allows users to: (1) visually explore DNN models with arbitrary input using a combination of node–link diagrams and matrix representation; (2) quickly identify activation values, weights, and feature map patterns within a network; (3) flexibly focus on visual information of interest with threshold, inspection, insight query, and tooltip operations; (4) discover network activation and training patterns through animation; and (5) compare differences between internal activation patterns for different inputs to the DNN. These functions allow neural network researchers to examine their DNN models from new perspectives, producing insights on how these models function. Clustering and summarization techniques are employed to support large convolutional and fully connected layers. Based on several part of speech models with different structure and size, we present multiple use cases where visualization facilitates an understanding of the models.

Visualizing Deep Neural Networks for Text Analytics

Existing storyline visualization techniques represent narratives as a node-link graph where a sequence of links shows the evolution of causal and temporal relationships between characters in the narrative. These techniques make a number of simplifying assumptions about the narrative structure, however. They assume that all narratives progress linearly in time, with a well defined beginning, middle, and end. They assume that at least two participants interact at every event. Finally, they assume that all events in the narrative occur along a single timeline. Thus, while existing techniques are suitable for visualizing linear narratives, they are not well suited for visualizing narratives with multiple timelines, nor for narratives that contain events with only one participant. In this paper we present Yarn, a system for generating and visualizing narratives with multiple timelines. Along with multi-participant events, Yarn can also visualize single-participant events in the narrative. Additionally, Yarn enables pairwise comparison of the multiple narrative timelines.

Kalpesh Padia

Papers

Visualizing digital collections at archive-it

A system for generating storyline visualizations using hierarchical task network planning

Automatically constructing training sets for electronic sentiment analysis

Visualizing Deep Neural Networks for Text Analytics

Yarn: Generating Storyline Visualizations Using HTN Planning