Paul Logasa Bogen

Longitudinal study of changes in blogs

Web-based distributed collections often include links to documents that are expected to change frequently, such as blogs. The study reported here demonstrates that blog changes follow specific patterns. The results also illustrate the substantial role of standardized templates in blog pages. These results extend our earlier models that assess the significance of Web page change from a human perspective. These improved models will enable software systems to assist human collection managers in identifying unexpected changes and aberrant events.

Enhancing digital libraries with social navigation: the case of ensemble

A traditional library is a social place, however the social nature of the library is typically lost when the library goes digital. This paper argues social navigation, an important group of social information access techniques, could be used to replicate some social features of traditional libraries and to enhance the user experience. Using the case of Ensemble, a major educational digital library, the paper describes how social navigation could be used to extend digital library portals, how social wisdom can be collected, and how it can be used to guide portal users to valuable resources.

Dynamically growing hypertext collections

Many approaches have been pursued over the years to facilitate creating, organizing, and sharing collections of materials extracted from large information spaces. Little attention, in the context of hypertext collections, has been paid to the addition of new materials to these collections over time. Traditionally, human maintainers manually incorporate new materials into existing collections as they appear in the underlying network. In this paper we address the issues involved in supporting the creation and maintenance of dynamically growing hypertextual collections. We describe a prototype implementation for automatically including additional, relevant materials into Web-based collections. Our prototype uses the metaphor of hypertextual paths, a proven technique for layering metastructure atop existing hypertextual materials, which is particularly well suited to accommodating growing collections.

WPv4: a re-imagined Walden's paths to support diverse user communities

The Waldens Paths Project, as part of our philosophy of continual evaluation, seeks out user communities who may find our tool useful. However, our users, in the last few years, have reported a series of common issues and desired features. In order to support our users, we initiated a redesign of Waldens Paths to solve these problems and enable us to rapidly prototype and experiment with features and interfaces. In order to accomplish these goals, we have created a web service that handles the storage and representation of our Path data structure. This service is isolated from user interface layers, allowing multiple interface designs to be implemented on top of the same Path data structures. Our prototype interfaces also represent new areas for Paths such as collaborative work, offline presentation, and mobile computing.

Redeye: a digital library for forensic document triage

Forensic document analysis has become an important aspect of investigation of many different kinds of crimes from money laundering to fraud and from cybercrime to smuggling. The current workflow for analysts includes powerful tools, such as Palantir and Analysts Notebook, for moving from evidence to actionable intelligence and tools for finding documents among the millions of files on a hard disk, such as Forensic Toolkit (FTK). Analysts often leave the process of sorting through collections of seized documents to filter out noise from actual evidence to highly labor-intensive manual efforts. This paper presents the Redeye Analysis Workbench, a tool to help analysts move from manual sorting of a collection of documents to performing intelligent document triage over a digital library. We will discuss the tools and techniques we build upon in addition to an in-depth discussion of our tool and how it addresses two major use cases we observed analysts performing. Finally, we also include a new layout algorithm for radial graphs that is used to visualize clusters of documents in our system.

Collaborative authoring of walden's paths

This paper presents a prototype of an authoring tool to allow users to collaboratively build, annotate, manage, share and reuse collections of distributed resources from the World Wide Web. This extends on the Waldens Path projects work to help educators bring resources found on the World Wide Web into a linear contextualized structure. The introduction of collaborative authoring feature fosters collaborative learning activities through social interaction among participants, where participants can coauthor paths in groups. Besides, the prototype supports path sharing, branching and reusing; specifically, individual participant can contribute to the group with private collections of knowledge resources; paths completed by group can be shared among group members, such that participants can tailor, extend, reorder and/or replace nodes to have sub versions of shared paths for different information needs.

Matisse: A visual analytics system for exploring emotion trends in social media text streams

Dynamically mining textual information streams to gain real-time situational awareness is especially challenging with social media systems where throughput and velocity properties push the limits of a static analytical approach. In this paper, we describe an interactive visual analytics system, called Matisse, that aids with the discovery and investigation of trends in streaming text. Matisse addresses the challenges inherent to text stream mining through the following technical contributions: (1) robust stream data management, (2) automated sentiment/emotion analytics, (3) interactive coordinated visualizations, and (4) a flexible drill-down interaction scheme that accesses multiple levels of detail. In addition to positive/negative sentiment prediction, Matisse provides fine-grained emotion classification based on Valence, Arousal, and Dominance dimensions and a novel machine learning process. Information from the sentiment/emotion analytics are fused with raw data and summary information to feed temporal, geospatial, term frequency, and scatterplot visualizations using a multi-scale, coordinated interaction model. After describing these techniques, we conclude with a practical case study focused on analyzing the Twitter sample stream during the week of the 2013 Boston Marathon bombings. The case study demonstrates the effectiveness of Matisse at providing guided situational awareness of significant trends in social media streams by orchestrating computational power and human cognition.

Categorization of computing education resources with utilization of crowdsourcing

The Ensemble Portal harvests resources from multiple heterogeneous federated collections. Managing these dynamically increasing collections requires an automatic mechanism to categorize records in to corresponding topics. We propose an approach to use existing ACM DL metadata to build classifiers for harvested resources in the Ensemble project. We also present our experience with utilizing the Amazon Mechanical Turk platform to build ground truth training data sets from Ensemble collections.

Template-based authoring of educational artifacts

The Waldens paths project is developing tools for leveraging student learning with the incredible amount of educational material on the Web. Specialized templates based on established educational frameworks, learning theories, or activities aid path authors in creating pedagogically sound paths by guiding them in collecting and structuring the information included in the path. We describe a template based on the inquiry-based learning educational framework and an implementation that provides support in applying the template to the path authoring process

A quantitative evaluation of techniques for detection of abnormal change events in blogs.

While most digital collections have limited forms of change--primarily creation and deletion of additional resources--there exists a class of digital collections that undergoes additional kinds of change. These collections are made up of resources that are distributed across the Internet and brought together into a collection via hyperlinking. Resources in these collections can be expected to change as time goes on. Part of the difficulty in maintaining these collections is determining if a changed page is still a valid member of the collection. Others have tried to address this problem by measuring change and defining a maximum allowed threshold of change, however, these methods treat all change as a potential problem and treat web content as a static document despite its intrinsically dynamic nature. Instead, we approach the significance of change on the web as a normal part of a web documents life-cycle and determine the difference between what a maintainer expects a page to do and what it actually does. In this work we evaluate the different options for extractors and analyzers in order to determine the best options from a suite of techniques. The evaluation used a human-generated ground-truth set of blog changes. The results of this work showed a statistically significant improvement over a range of traditional threshold techniques when applied to our collection of tagged blog changes.