HCI Bibliography Home | HCI Conferences | HCIR Archive | Detailed Records | RefWorks | EndNote | Hide Abstracts
HCIR Tables of Contents: 07080910111213

Proceedings of the Workshop on Human-Computer Interaction and Information Retrieval

Fullname:Proceedings of the Workshop on Human-Computer Interaction and Information Retrieval
Location:Rutgers, New Brunswick, New Jersey
Standard No:hcibib: HCIR10
Links:Conference Website and Proceedings | Papers | Posters | Full Proceedings
  1. Papers
  2. Posters/Demos


VISTO: for Web Information Gathering and Organization BIBAPDF 1
  Anwar Alhenshiri; Carolyn Watters; Michael Shepherd
This paper presents a VIsual Search Task Organizer (VISTO). VISTO is a visual tool with effective information gathering task capabilities for the Web. In this prototype system, the task of Web information gathering is taken into consideration with respect to how user locate information for the task, organize task information, preserve and re-find task information, and compare information for effective reasoning and decision making. VISTO was designed and built based on recommendations from previous studies in a larger research. The prototype is ready to be evaluated in the next step of the research.
Time-based Exploration of News Archives BIBAPDF 2
  Omar Alonso; Klaus Berberich; Srikanta Bedathur; Gerhard Weikum
In this paper, we present NEAT, a prototype system that provides an exploration interface to news archive search. Our prototype visualizes search results making use of two kinds of temporal information, namely, news articles' publication dates but also their contained temporal expressions. The displayed timelines are annotated with major events, harvested using crowdsourcing, to make it easier for users to put the shown search results into context. The prototype has been fully implemented and deployed on the New York Times Annotated Corpus.
Combining Computational Analyses and Interactive Visualization to Enhance Information Retrieval BIBAPDF 3
  Carsten Goerg; Jaeyeon Kihm; Jaegul Choo; Zhicheng Liu; Sivasailam Muthiah; Haesun Park; John Stasko
Exploratory search and information-seeking support systems attempt to go beyond simple information retrieval and assist people with exploration, investigation, learning and understanding activities on document collections. In this work we integrate several computational text analysis techniques, including document summarization, document similarity, document clustering, and sentiment analysis, within the interactive visualization system Jigsaw in order to provide a flexible and powerful environment for people to examine sets of documents. Our focus is not on cutting edge algorithms for computational analysis but rather on the process of integrating automated analyses with interactive visualizations in a smooth and fluid manner. We illustrate this integration through an example scenario of a consumer examining a collections of car reviews in order to learn more about the car and understand its strengths and weaknesses.
Impact of Retrieval Precision on Perceived Difficulty and Other User Measures BIBAPDF 4
  Mark Smucker; Chandra Prakash Jethani
When creating interactive retrieval systems, we want to reduce the perceived difficulty of finding relevant documents. We conducted a user study that controlled retrieval precision. We found that a higher retrieval precision caused a reduction in perceived difficulty compared to a lower retrieval precision. We also found that higher precision increases enjoyment and has some influence on ability to concentrate, but we found no evidence that precision keeps the user engaged vs. bored with the search.
Exploratory Searching As Conceptual Exploration BIBAPDF 5
  Pertti Vakkari
The aim of this paper is to analyze the characteristics of exploratory searching for inferring ideas on how to evaluate exploratory search systems. Exploratory searching is defined as conceptual exploration. Information search process is divided into major stages. Goals, criteria and measures of attaining goals in explicating information need and formulating search are proposed. They can be applied for evaluating search systems aiming at supporting these two stages in searching.
Casual-leisure Searching: The Exploratory Search Scenarios that Break our Current Models BIBAPDF 6
  Max L. Wilson; David Elsweiler
In trying to understand Exploratory Search, the community has focused on users who are working towards an information need, but who are unclear of their goal, technology, or domain of information. Our recent research, however, suggests that this definition misses perhaps the most exploratory search scenario of all -- scenarios where the goal is not information-oriented. We present combined evidence from two on-going research projects, which demonstrates that such situations occur regularly within casual-leisure situations. We use our findings to characterise such tasks and suggest that casual-leisure search scenarios deserve more focus as we work towards supporting exploratory search.


Improving Web Search for Information Gathering: Visualization in Effect BIBAPDF 7
  Anwar Alhenshiri; Carolyn Watters; Michael Shepherd
The nature of the Web implies heterogeneity, large volumes, and varied structures. Hence, finding results that best suit the needs of every individual in every type of Web task is a very challenging problem. This research presents an interactive Visual Search Engine (VSE) in which both query reformulation and results presentation are visualized. The paper presents the results of a user study in which the effectiveness of the VSE compare to Google is evaluated. The VSE was shown to be effective with respect to Web information gathering tasks.
User-oriented and Eye-Tracking-based Evaluation of an Interactive Search System BIBAPDF 8
  Thomas Beckers; Norbert Fuhr
We report on experiences and challenges we faced during an user-oriented eye-tracking-based evaluation of an interactive search system. Furthermore, some exemplary analyses were performed. Finally, we specify requirements for the design and architecture of search systems amenable for eye-tracking.
Exploring Combinations of Sources for Interaction Features for Document Re-ranking BIBAPDF 9
  Emanuele Di Buccio; Massimo Melucci; Dawei Song
The behavior of the user when interacting with a result page or the corresponding landing documents is a possible source of evidence that Information Retrieval (IR) systems can exploit to assist the user when searching for information. Interaction features can be adopted as evidence to model the user behavior, thus making it usable to assist relevance prediction. One issue when dealing with interaction features is the selection of the sources from which these features are distilled. Individual users and group of users which perform a similar task or look for information matching the same query are possible sources. This paper will focus on these two sources, particularly investigating group of users searching for the same topic as source for interaction features to be used as an alternative to, or in combination with, individual users. The objective of this work is to investigate the impact of diverse combinations of these sources on the retrieval effectiveness, specifically when interaction features are used as evidence to support document re-ranking.
Extracting Expertise to Facilitate Exploratory Search and Information Discovery: Combining Information Retrieval Techniques with a Computational Cognitive Model BIBAPDF 10
  Wai-Tat Fu; Wei Dong
We compared and combined the traditional information retrieval (IR) methods of expert identification with a computational cognitive model to test their effectiveness in facilitating exploratory search performance using a data set from a large-scale social tagging system. We found that the two methods of expert identification, although based on different assumptions, were in general consistent in extracting useful structures for exploratory search. The methods, however, did show systematic differences in their effectiveness to guide users to find popular vs less popular topics. The findings have important implications on presentations of information cues that facilitate interactive IR and discovery.
An Architecture for Real-time Textual Query Term Extraction from Images BIBAPDF 11
  Cathal Hoare; Humphrey Sorensen
This paper presents an approach that generates a set of search queries from a user's query image. The approach provides the ability to query one's environment in real-time, effectively allowing a user to ask "What is that?". This is achieved by capturing the user's context through a geotagged photograph, and using it to filter a community image collection, for example Flickr, to retrieve a set of descriptive tags; these tags are processed and used as query terms. Having discussed the role of context in the application and the service's architecture, an initial study of the benefits of this approach will be presented.
Transaction Log Analysis of User Actions in a Faceted Library Catalog Interface BIBAPDF 12
  Bill Kules; Robert Capra; Joseph Ryan
In this paper, we report preliminary findings from an analysis of searcher actions in a faceted library catalog. In this comparative laboratory study (N=18) searchers were asked to conduct exploratory searches. For the control group facet use accounted for approximately 14% of logged actions. For participants who were shown a 60 second video about how to use facets, facet use accounted for approximately 21% of actions. We also observed differences in sequences of actions that participants undertook during their searches that suggest that searchers who watched the facet training video used facets at key points in their search process such as just after issuing a search and just before adding an item to their "book bag".
Context in Health Information Retrieval: What and Where BIBAPDF 13
  Carla Lopes; Cristina Ribeiro
Researchers are aware that context acts information retrieval in general. The health area is no exception and is particularly rich in terms of context. To understand how context is used in health information research, we collected a sample of health information research papers that use context features. Papers were analyzed and classified according to the type of context features and to the stage of the retrieval process into which they were incorporated. Further, we also identified the specific context features used in each category of features and each stage of the process. Results show a weaker use of interaction context features than we expected and, as supposed, a large use of collective features. A considerable number of papers use context to query related activities. We also found that research is mainly aimed at health professionals, suggesting a gap in health consumers research that should be explored.
Tactics for Information Search in a Public and an Academic Library Catalog with Faceted Interfaces BIBAPDF 14
  Xi Niu; Bradley M. Hemminger
This study examined a large number of searches conducted when the users are interacting with two Endeca-based faceted library catalogs (University of North Carolina at Chapel Hill [UNC] Library catalog and Phoenix Public Library [PPL] catalog). The goal is to investigate people's search tactics with the faceted catalogs in an academic library and a public library environment. Two large data sets (with 504,142 logs for 40 days, and 1,010,239 logs for 60 days respectively) are analyzed. State transition analysis and maximal repeating patterns [MRP] analysis are conducted to identify the search tactics and action patterns. The results have both implications for designers in developing faceted library catalogs, and methodological contributions to the empirical research on faceted search systems.
Understanding Information Seeking in the Patent Domain and its Impact on the Interface Design of IR Systems BIBAPDF 15
  Daniela Becks; Matthias Görtz; Christa Womser-Hacker
In this position paper, we highlight the need for understanding and modeling a user's context when designing the user interface of an information retrieval system using the example of the patent domain. Based on fundamental concepts of information seeking and retrieval research, we describe the different contextual factors characteristic for this domain and common task scenarios of patent retrieval. Finally, we outline first starting points for coping with these domain-specific conditions in the interface design of IR systems and discuss future research needs.
Better Search Applications Through Domain Specific Context Descriptions BIBAPDF 16
  Corrado Boscarino; Arjen P. de Vries; Jacco van Ossenbruggen
There is a wide agreement that a user centred approach to IR applications design outperforms system centred ones. A classic understanding of this design approach, and specifically of its underlying notion of context, appeared however insufficient to explain the results of a pilot experiment. We recognise the importance of context, but we define context differently by means of a domain theory: a conceptualisation of the domain at hand, preferably developed within the same community which users belong to.
Layered, Adaptive Results: Interaction Concepts for Large, Heterogeneous Data Sets BIBAPDF 17
  Duane Degler
Some data environments are not well served by current styles of search results presentation. One example of this is large-scale archival, library or museum collections. The range of user goals and interaction needs can be quite broad, and the information itself is highly structured yet very heterogeneous -- it spans many subject areas, information types, and presentation/media. Based on the use of semantic web formats for metadata, we believe it is possible to leverage the semantic relationships to drive aspects of results presentation -- to change elements of the UI itself in response to the results data. We present these concepts as a catalyst for discussion with the HCIR research community, exploring how semantic structures can support arrangement and components available for refining search results sets, and thus make the interface more responsive to user's goals and needs.
Revisiting Exploratory Search from the HCI Perspective BIBAPDF 18
  Abdigani Diriye; Max L. Wilson; Ann Blandford; Anastasios Tombros
In this paper, we revisit the definition of Exploratory Search tasks after 4 years of contributions from the Information Seeking and Retrieval community. We consolidate the factors that influence an exploratory search task: objective, search activities, conceptual complexity, and procedural complexity, and introduce a new factor: domain knowledge. We hypothesize that, in order to support Exploratory Search tasks efficiently, we must consider all the factors from an HCI perspective.
Supporting Task with Information Appliances: Taxonomy of Needs BIBAPDF 19
  Sarah Gilbert; Lori McCay-Peet; Elaine Toms
Integrating search systems with task environments to create task-specific information appliances will most likely represent the next wave of technologies. At present, search systems are for the most part isolated from the actual task environment. In this paper we have identified one task environment -- that of the student writing a term paper -- to propose sets of needs that should to be supported by tools. In addition, the process of completing the task illustrates how search needs change in level of specificity over the life of the task.
A Proposal for Measuring and Implementing Group's Affective Relevance in Collaborative Information Seeking BIBAPDF 20
  Roberto González-Ibáñez; Chirag Shah
In an interactive information-seeking environment, it is important to consider more user-centric notion of relevance, which includes motivational and affective relevance. In this article we introduce the notion of group's affective relevance for collaborative information seeking. We explore different ways of measuring it and examine how these measures are related to the performance of teams. In addition, we propose a new model for implementing group's affective relevance in information systems that provide support for collaborative information seeking.
Evaluation of Music Information Retrieval: Towards a User-Centered Approach BIBAPDF 21
  Xiao Hu; Jingjing Liu
With the dramatic increase of online digital music, research on Music Information Retrieval (MIR) is flourishing more than ever. However, evaluation in MIR has been focused on system-centered approaches, where systems are evaluated against a pre-built ground truth dataset using system-focused measurements, and little attention has been spent on user experience. In this paper, we argue that MIR evaluation should take users, in addition to systems, into consideration. We suggest that some measures and models in the established area of Interactive IR in the text domain can be applied to the MIR domain. Novel evaluation measures that are unique to MIR are also proposed. The purpose of this paper is to encourage user-oriented, and thus more comprehensive, approaches to evaluating MIR systems.
Information Derivatives: A New Way to Examine Information Propagation BIBAPDF 22
  Chirag Shah
An increasing amount of information available online is dynamic in nature. That is, it constantly keeps changing with people consuming and adding their own value to it. We propose to study how such information flows from its original source to other locations through the concept of information derivatives. We treat information as an object and consider the original piece of information as the 0th derivative. Any subsequent use of that information produces 1st derivative, 2nd derivative, and so on. We provide a mathematical formulation of this phenomenon and propose a new framework to study information propagation in online sources, and to understand the dynamic nature of information.
Implicit Factors in Networked Information Feeds BIBAPDF 23
  Fred Stutzman
In recent years, the development of "News Feed" interfaces have transformed the ways in which individuals seek and encounter information in social network sites. Rather than primarily searching for information, a networked information feed provides a constantly updated stream of information about ongoing activity in the networked community. In the following paper, the components of networked information feeds are examined. Particular attention is paid to the variable forms of content included in networked information feeds, the effects of diversity in network composition on the networked information feed, and the implications of filtering networked information feeds.
Improving the Online News Experience BIBAPDF 24
  V. G. Vinod Vydiswaran; Raman Chandrasekar
News consumption patterns are changing, but the tools to view news are dominated by portal and search approaches. We suggest using a mix of search, visualization, natural language processing and machine learning to provide a more captivating, sticky news consumption experience. In this position paper, we suggest a design for one specific use-case where a user needs to catch up on news from a particular time period. The results need to cover key events that happened during the time period, but the stories should be prioritized based on the user's interests. Further, users should be able to interact and explore stories of interest. We present the limitations of existing online news sites for such a task and present some ways to address these issues.
Breaking Down the Assumptions of Faceted Search BIBAKPDF 25
  Vladimir Zelevinsky
In this paper, we list several features of faceted search and challenge their implicit assumptions.
Keywords: Faceted search, user interfaces, refinements, semantic networks, correlation, fuzzy matching
A Survey of User Interfaces in Content-based Image Search Engines on the Web BIBAPDF 26
  Danyang Zhang
Content-based image retrieval or CBIR technique has been researched for over a decade, and most researches have been focusing on image matching technologies such as feature extraction and similarity measurement. Recently, there has been an attempt to build content-based image search engines on the web in such a way that they could be as popular as their text-based counterparts. In order to do so, other key issues including user interface should also be explored. This paper presents the user interfaces of current content-based image search engines on the Internet, and analyzes their advantages and disadvantages.