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:Mountain View, California
Dates:2011-Oct-20
Standard No:hcibib: HCIR11
Papers:46
Links:Conference Website and Proceedings | Papers | Posters | Workshop Report
Summary:The 2011 Workshop on Human-Computer Interaction and Information Retrieval, now in its fifth year, workshop was held in October, in Mountain View, CA. The event brings together researchers from academia, industry, and government and a range of disciplines for in-depth discussions in an informal atmosphere. The workshop continues to grow, with around 100 attendees this year. We continued the HCIR Challenge, this time focusing on the problem of information availability, with four in-depth system demonstrations, and audience selection of a challenge winner.
  1. Papers
  2. Challenge Reports
  3. Posters

Papers

Search As You Think AND Think As You Search: Semantic Search Interface for Entity/Fact Retrieval BIBAPDF 1
  Sofia J. Athenikos; Xia Lin
The mode of information retrieval on the Web in general remains that of conventional keyword-based page/document retrieval. The project presented in this paper, called PanAnthropon FilmWorld, aims at demonstrating direct, sophisticated entity/fact retrieval by using semantic knowledge extracted from Wikipedia. To this end, a semantic knowledge base containing the extracted data and a semantic search interface demonstrating the proposed retrieval capability have been constructed. The focus of this paper is on the design and performance of the intelligent, interactive interface. The results of evaluation confirm the effectiveness of the interface for information retrieval by ordinary users with no prior exposure.
Conceptual Mile Markers for Exploratory Search BIBAPDF 2
  Keith Bagley; Haim Levkowitz
During exploratory search sessions, users often experience difficulty finding and re-finding high-quality results that are pertinent to their search goals. Various studies have found that search sessions are unsuccessful, end prematurely, and/or lead to user frustration. This paper describes a framework and prototypical system called Conceptual Mile Markers (CMM) that reduces the "time to value" for a search by matching a user query with existing search paths, thereby allowing users to profit from the "wisdom of the masses" and reuse previously successful search trails. Additionally, these search paths may be saved, shared, and retrieved later as a style of lightweight personalization without the need for explicit user tracking. We propose that our framework and prototype leads to users being more likely to acquire a successful end-state and high-quality results, while being less apt to get frustrated and/or abandon searches prematurely.
Diamond Browser: Faceted Search on Mobile Devices BIBAPDF 3
  Robert Capra; Jason Raitz
Faceted search interfaces are commonly used on the Web, especially on sites for online shopping, document collections, and library catalogs. As use of mobile web devices such as smartphones and tablet computers with smaller screens has increased, designers are adapting support for faceted search interfaces to meet the limitations of smaller screens. Although there have been a number of studies that have examined faceted search interfaces on traditional computer displays, few studies have explored the tradeoffs and use of smaller-screen faceted interfaces. In this paper, we present the Diamond Browser, a system we are building to rapidly design, test, and conduct evaluations of faceted search interface designs for mobile devices. We describe the system architecture and two initial interfaces that we developed.
User Domain Knowledge and Eye Movement Patterns During Search BIBAPDF 4
  Michael J. Cole; Jacek Gwizdka; Nicholas J. Belkin; Chang Liu
Cognitive effort measures inferred from eye movement patterns during textural information search have been correlated with subjective task difficulty and objective measures of task effort. Analysis of the same cognitive effort measurements in an independent user study (n=40) of recall-oriented search in the genomics domain reveals strong correlations with self-assessed domain knowledge. A simple regression model based on these measures was successful in predicting participant domain knowledge. These measurements of cognitive effort during search can be calculated on-the-fly and require only recent eye fixation location and duration. We discuss the potential for real time detection of domain knowledge during information search using this eye movement analysis technique.
Search interface feature evaluation in biosciences BIBAPDF 5
  Anna Divoli; Alyona Medelyan
This paper reports findings on desirable interface features for different search tasks in the biomedical domain. We conducted a user study where we asked bioscientists to evaluate the usefulness of autocomplete, query expansions, facetted refinement, related searches and results preview implementations in new pilot interfaces and publicly available systems while using baseline and their own queries. Our evaluation reveals that there is a preference for certain features depending on the search task. In addition, we touch on the current pain point of facetted search: the acquisition of faceted subject metadata for unstructured documents. We found a strong preference for prototypes displaying just a few facets generated based on either the query or the matching documents.
Document Usefulness: taking Genre to Task BIBAPDF 6
  Luanne Freund
This paper examines the relationship between three variables in the HCIR dynamic: information task type, document genre and usefulness. The ability of searchers to consistently label Web genres is also addressed. Results of a domain-specific (egovernment) user study with 25 participants indicate that usefulness varies significantly by task type and by genre of search results. Genre emerges as significant for information tasks related to Learning, Deciding or Doing, but not for Problem Solving or Fact-Finding. Participants found genre labeling difficult, and applied many labels to each document, resulting in low levels of precision (23%) and recall (52%) for the labeling exercise. However, as a group, participants chose the correct genre label most often for most genres, indicating that some consensus exists.
Designing for Collaboration in Information Seeking BIBAPDF 7
  Gene Golovchinsky; Abdigani Diriye; Jeremy Pickens
Information seeking is often a collaborative activity that can take many forms; in this paper we focus on explicit, intentional collaboration of small teams and explore a range of design decisions that should be considered when building Human-Computer Information Retrieval (HCIR) tools that support collaboration. In particular, we are interested in exploring the interplay between algorithmic mediation of collaboration and the mediated communication among team members. We argue that certain characteristics of the group's information need call for different design decisions.
Evaluating an Associative Browsing Model by Simulation BIBAPDF 8
  Jinyoung Kim; W. Bruce Croft; David A. Smith
In our previous work [5, 8], we proposed an associative browsing model of personal information in which users can navigate through the space of personal items. In this paper, we evaluate the associative browsing model using simulation in the context of known-item finding task. We built a model of user which is parameterized to simulate various aspect of user, and performed experiments to evaluate the associative browsing model under various conditions.
   We find that user's level of knowledge and other characteristics act their known-item finding behavior. The results is also consistent with our earlier user-based evaluation [8], showing that the associative browsing model can play a role complementary to keyword search in known-item finding.
Visualizing Stages During an Exploratory Search Session BIBAPDF 9
  Bill Kules; Robert Capra
We report on findings from a laboratory study in which participants completed tasks using a faceted search interface to an online library catalog. Using a retrospective stimulated recall technique, participants gave self-reports on what stage of search they were engaged in at various points in the search session. We found that on average, participants spent the most time extracting information from results, but all the stages investigated played important roles. Deciding on query terms and getting an overview of results were common early in the search process, whereas spending time deciding on the next step to take were often observed later in a search.
Knowledge Examination in Multi-Session Tasks BIBAPDF 10
  Jingjing Liu; Nicholas J. Belkin
We report findings on the patterns of change in users' self-rated topic knowledge in multi-session search tasks. Data came from a 3-session lab experiment with 24 participants, each working on one sub-task in a general task at one session, searching for information and writing reports on hybrid cars. The general task was either parallel or dependently structured. Examination was conducted for users' knowledge of both the general tasks and the sub-tasks, both before and after the working sessions. Results demonstrated that users' knowledge of general tasks and that of sub-tasks had different values and patterns of change. We also found that some attributes of users' knowledge varied between task types. These findings further our understanding of users' knowledge in information tasks and are helpful for information retrieval research and system design.
Exploring the Effect of Task Difficulty and Domain Knowledge on Dwell times BIBAPDF 11
  Chang Liu; Michael Cole; Nicholas Belkin; Jacek Gwizdka; Xiangmin Zhang
This study explores the effect of task difficulty on users' search behaviors, i.e. dwell time on content pages and search result pages, by users with high and low domain knowledge. A user experiment was conducted, with 40 participants working on 5 search tasks. Participants were divided into two domain knowledge levels according to their MeSH term ratings. Among the five search tasks, three were Difficult tasks and the other two were Easy tasks. Our results demonstrated that there was interaction effect of task difficulty and domain knowledge on the dwell time on content pages. We also found that task difficulty and domain knowledge have main effect on the dwell time on search result pages. In particular, the dwell time on search result pages was much higher in Difficult tasks or by users with low domain knowledge. The results indicated that the dwell time on search result pages was better indicator of task difficulty than dwell time on content pages. Our results have implications for personalization information retrieval.
An Analysis of User Strategies for Examining and Processing Ranked Lists of Documents BIBAPDF 12
  Mark D. Smucker
The predominant display of document retrieval results is a ranked list of query-biased summaries. When examining and processing search results, users must make complex decisions about how to allocate their time and relevance judging effort between evaluation of summaries and the full documents reachable with a mouse click on a summary. We performed a cluster analysis of the search results processing behavior of 48 user study participants. This analysis produced three clusters of behavior. Across these clusters, we found participants to employ two approaches to the evaluation of summaries: fast and liberal, or slow and neutral. Liberal judges of summaries tolerate clicking on non-relevant summaries in an effort to avoid missing relevant documents. The best performing group employed a fast and liberal approach to summaries and also quickly evaluated full documents. The two lower performing groups utilized opposite strategies with one group trading a short amount of time on the summaries for more time spent evaluating full documents and the other group invested more time in evaluating summaries and spent a shorter time on documents.
An Exploratory Study of the Effect of Cognitive Styles on User Performance in an Information System BIBAPDF 13
  Xiaojun Yuan; Jingjing Liu
This study investigated the effect of cognitive styles on users' information-seeking task performance using an information system called Web of Science. Sixteen graduate students participated in a user experiment. Each completed an extended cognitive style analysis wholistic analytic test (Extended CSAWA test) on cognitive style, and then conducted eight tasks in the Web of Science system. Results demonstrated that users' cognitive styles did not impact their search performance. Some thoughts and future work were discussed.
Using Social Tags and Controlled Vocabularies As Filters for Searching and Browsing: A Health Science Experiment BIBAPDF 14
  Michael Zarro; Xia Lin
The retrieval of health information on the Web is limited by the vocabulary gap between the human searcher and the terms used by authors of medical documents. Social tagging and Medical Subject Headings (MeSH) have the potential to help close this gap by providing peer and professionally created terms that may be valuable in guiding searchers to health information resources. Search interfaces that provide terms to modify or expand health-related queries can help searchers fully explore unfamiliar concepts. In this paper we present a search system enhanced with social tags and MeSH terms, and report the results of an experiment exploring its use. Our prototype interface exposed terms to users that could be used to modify search queries, and was rated useful by participants in a user study.

Challenge Reports

FreeSearch -- Literature Search in a Natural Way BIBAPDF 15
  Claudiu S. Firan; Wolfgang Nejdl; Mihai Georgescu; Xinyun Sun
In the FreeSearch project we develop new methods for simple literature search that works on any catalogs, without requiring in-depth knowledge of the metadata schema. FreeSearch helps users proactively and unobtrusively by guessing at each step what the user's real information need is and providing precise suggestions.
Session-based search with Querium BIBAPDF 16
  Gene Golovchinsky; Abdigani Diriye
We illustrate the use of Querium, a novel search system designed to support people's collaborative and multi-session search tasks, in the context of the HCIR 2011 Search Challenge. This report demonstrates how a Querium's interface and search engine can be used to search for documents in an open-ended, exploratory task. We illustrate the use of relevance feedback, faceted search, query fusion, and the search history, as well as commenting and overview functions.
GisterPro BIBAPDF 17
  David L. Ostby; Edmond Brian
GisterPRO is a Cloud-Powered Exploratory Search tool designed to maximize relevant results: increasing both Precision and Recall. The science and technology were created to meet the demands of today's Intelligence Community analyst conducting Open Source Intelligence (OSINT). The tool is optimized for unstructured data and particularly powerful for users plumbing unfamiliar subject domains uncertain if answers to fuzzy questions even exist. Baked into the GisterPRO technology continuum are automated processes including feature extraction, entity extraction, disambiguation and high-speed reading and relationship finding in unstructured data.
Query Analytics Workbench BIBAPDF 18
  Antony Scerri; Matthew Corkum; Keith Gutfreund; A Ron Daniel Jr.; Michael Taylor
In this paper we describe the Query Analytics Workbench (QAW), a tool created by our team for the 2011 HCIR Challenge to address the information availability problem described in the Challenge. Our tool is designed to support search queries that are either hard to express or are more involved than a typical search. QAW is a search application that incorporates both exploration and progressive refinement activities. Its main focus is to guide the user through constructing their query. It offers seven different filters and analytical components that help users perform complex queries, via an iterative progressive query refinement.

Posters

Analyzing User Behavior Patterns in Adaptive Exploratory Search Systems with LifeFlow BIBAPDF 19
  Jae-wook Ahn; Krist Wongsuphasawat; Peter Brusilovsky
Adaptive exploratory search is a method that can provide user-centered personalized search results by incorporating interactive user interfaces. Analyzing the user behavior patterns of these systems can be complicated when they support transparent and controllable open user models. This paper suggests to use a visualization tool to address the problem, as a complement to the typical statistical analysis. By adopting an event sequence visualization tool called LifeFlow, we were able to easily find out user interesting behavior patterns, especially regarding the open user model exploration.
Collective Information Seeking BIBPDF 20
  Scott Bateman; Carl Gutwin; Gordon McCalla; Ryen White
The potential of a 'high density' image retrieval interface BIBAPDF 21
  Richard Butterworth; Ayse Göker
Images have very different properties as information carrying units than documents do. Much of the academic work in image seeking and retrieval has its roots in the more traditional field of information seeking and retrieval where the vehicle for transmitting information is the document. In this position paper we argue that typical image retrieval systems look very much like document retrieval systems (search terms are entered, and a relevance ordered list of image thumbnails, with a few tens of images per screen is presented to the user) and that in many (though not all) image seeking scenarios this is not the most appropriate interface design. We argue that a 'high density' image retrieval interface that presents the user with several hundred image thumbnails at once, firstly need not necessarily overwhelm the user, and secondly may greatly assist certain classes of users in their image seeking tasks. We outline the design of a high density image retrieval interface, and then look at existing models of image seeking needs and tasks and argue that certain classes of users would benefit from such an interface.
Exploring Growing Information Spaces BIBAPDF 22
  Marian Dörk; Sheelagh Carpendale; Carey Williamson
Growing information spaces bring not only informational challenges, but also new opportunities for exploration. Drawing from maps as an analogy, we conceptualize information seekers as explorers of expanding information landscapes. While text has been the dominant frame of reference for information-seeking interfaces, visualization has the potential to expose faceted overviews and provide many ways of seeing information. Considering recent technological trends on the Web, many new forms of information seeking are feasible that utilize rich semantics and interactive graphics. With these developments on our side, we advocate a shift from information needs and relevance to more open-ended exploration and discovery of growing information spaces.
A Method to Evaluate the Synergic Effect in Collaborative Information Seeking BIBAPDF 23
  Roberto González-Ibáñez; Chirag Shah; Muge Haseki
One of the strongest appeals of collaboration is that it allows collaborators achieve something greater than the sum of their individual contributions. This notion, which we referred to as synergy, has been understudied in information seeking domain. To address this shortcoming, here we outline an approach to study and evaluate the synergic effect in collaborative information seeking (CIS). Our main contributions consist of a method of evaluation, a set of measures, and a system for experimentation. This approach has been applied to several of our recent works relating to CIS, and shown to be very promising for studying user-driven collaborative projects.
Least Effort? Not If I Can Search More BIBAPDF 24
  Jacek Gwizdka; Michael Cole
Increasing effort of obtaining information is expected to lead to worse performance. Our results from a controlled web search and navigation study show that the relationship between effort and search task complexity is different for low and high cognitive ability users. Higher cognitive ability searchers were faster than low ability searchers on simpler tasks and in an interface that contained overview of search results, while both groups entered about same number of queries. In contrast, the high cognitive ability group tended to perform more actions than the low ability group under conditions of increased difficulty, yet their task outcomes did not show the benefit of the extra effort invested in the task performance. We offer some plausible explanations supported by interaction data and by eye-movement data.
Making sense of time: timeline visualization for public transport schedule BIBAPDF 25
  Khandaker Tabin Hasan; Sheak Rashed Haider Noori; Abdus Salam; Md. Anwarul Kabir
The numerical values of time expressed through 24 hours cycle of a day hardly enables to grasp the real sense of time. The perception of day and night requires some extra cognitive effort in general and in travel option in particular. The study focuses on a practical scenario of choosing a public transport system where a set of time and its durations are presented in conventional time format. Travel options are presented in alpha-numeric form where a person may overlook valuable aspects of time associated with journey and often may lead to various degree of discomfort like arriving at the mid-night or long agonizing waiting in transits. Considering the departure time, arrival time, number of transits and their lengths, and the overall length of journey as key ingredients for choosing the right travel option, we find that most people do compromise in some way while a better option is overlooked. In this paper, we have addressed the travel ingredients in the frame of a day for person to pick a better option. Our solution offers a timeline-based graphical visualization of temporal data providing the sense of time in its spatiotemporal sphere. We developed timeline-based visualization, in comparison with the existing textual visualization shows a substantial improvement in making the right choice for a travel, what we call "making sense of time."
User Evaluation of an Interactive Music Information Retrieval System BIBAPDF 26
  Xiao Hu; Noriko Kando; Xiaojun Yuan
Music information retrieval (MIR) is a highly interactive process and MIR systems should support users' interactions during the process. However, there are very few user-centered experiments in evaluating interactive MIR systems. In this paper, we present a user experiment with 32 participants evaluating two result presentation modes of a music mood recommendation system for two music seeking tasks, using user-centered measures. Preliminary results disclosed that the presentation modes made significant difference on some of the user-centered measures and users may enjoy the less effective but more appealing mode.
Using Social Annotations for Trend Discovery in Scientific Publications BIBAPDF 27
  Meiqun Hu; Ee-Peng Lim; Jing Jiang
Social tags and citing documents are two forms of social annotations to scientific publications. These social annotations provide useful contextual and temporal information for the annotated work, which encapsulates the attention and interest of the annotators. In this work, we explore the use of social annotations for discovering trends in scientific publications. We propose a trend discovery process that employs trend estimation and trend selection and ranking for analyzing the emerging trends shown in the social annotation profiles. The proposed sigmoid trend estimator allows us to characterize and compare how much, when and how fast the trends emerge. To perform topic-specific trend analysis, we further adopt topic modeling on the annotation content to decapsulate the multitude of impact created by the annotated work.
On the Value of Page-Level Interactions in Web Search BIBAPDF 28
  Jeff Huang
Users' search data has been useful for understanding search behavior and has been applied to improve web search. Query logs, the primary source of search data in recent information retrieval research, are limited in expressing the user's behaviors; they omit behaviors that do not hit the web server: cursor movements, scrolling, browser tab usage, text highlighting, and duration of a pageview. These actions we call 'page-level interactions'; they can be collected by search systems using client-side scripting, but this is currently not being done by web search engines. Previous studies in related fields have shown that adding additional independent data provides greater improvements than smarter algorithms. Since page-level interaction data is independent from query and click data, collecting and mining page-level interactions may be one direction that search engines can pursue to innovate. These interactions can supplement query logs by helping understanding user intent, disentangling interleaved queries, or providing richer user data for rare queries; they can be particularly useful especially when clicks for queries are unavailable or insufficient.
Understanding the Information Needs and Search Behaviors of Mobile Users BIBAPDF 29
  Dima Kassab; Xiaojun Yuan
This research investigated why and how users employ mobile phones or other small screen devices to access and acquire information in order to better understand human mobile information behavior. In this paper, we present the results of 12 interviews conducted on a one-to-one basis with graduate students regarding their information needs and searching habits through mobile devices. Particularly, their mobile intent, and their search mobile behavior were discussed in detail. We hope the current research can give insights and frame directions for future research, as well as to reveal any new trends in mobile users' behaviors.
Search Quality Differences in Native and Foreign Language Searching BIBAPDF 30
  Anita Komlodi; Eszter Jozsa; Mate Koles; Karoly Hercegfi
Search engine users may carry out internet searches in a foreign language for a variety of reasons: they may be immigrants in a new country, international students moving to a new culture to pursue studies, or travelers planning a trip to a country unknown. Users may also search in a foreign language in the hopes of obtaining more and better content on the topic of their search. Whatever the reason, when searching in a foreign language for content that was created in an unfamiliar culture, searchers face a myriad of problems: they may speak the language but not grasp the slight variations in meaning that will change their search results drastically, they may not be aware of trustworthy sources, and they may face unfamiliar information architecture and design styles in websites. This paper presents preliminary results from a study examining users' searching in their native and foreign languages. Differences in search quality in native and foreign languages are reported in this paper.
Faceted Search Log Query Analysis BIBAPDF 31
  Jonathan Koren
In this paper we present an analysis of search logs of a faceted search interface of LinkedIn, a popular social network with approximately 100 million users. 115 million search sessions from 22 million distinct users were collected. This analysis focuses on how users utilize facets in concert with traditional keyword search, what types of facets users are more likely to find useful.
   This analysis can be used to improve facet and facet-value ranking algorithms and improve models of user behavior. We believe that this one of a few public analyses of facet search system, and the first analysis of this size, and also that considers social network search.
Is it Time to Abandon Abandonment? BIBAPDF 32
  Abhimanyu Lad; Daniel Tunkelang
Commonly used click-based measures like abandonment and mean reciprocal rank (MRR) present an incomplete, and often misleading, picture of search performance, especially in rich user interfaces that support a wide range of search behaviors. We propose a search utility framework that is based on a holistic view of the information-seeking process. First, we go beyond the use of clicks as indicators of relevance, taking into account actions performed on search results as more reliable indicators of completion of the user's underlying task. Second, instead of looking only at individual queries, we consider the entire search session comprising multiple queries that are meant to address a single information need. We argue that an evaluation metric that combines these two features more accurately reflects the effectiveness of the system as perceived by the user. Finally, we propose future experiments to operationalize as well as validate this framework.
Towards conversational interfaces to web applications BIBAPDF 33
  Tessa Lau; Julian Cerruti; Morgan Dixon; Jeffrey Nichols
Today's conversational interfaces are largely based on the paradigm of information retrieval from databases. In this position paper, we propose a radically different approach: building CIs on top of existing web applications. Such a system will draw together research in task modeling, web usage mining, information extraction, as well as the vast amount of existing research on traditional CIs.
CODEcomp: Deconstructing Energy Codes BIBAPDF 34
  Michael Madison
This paper describes CODEcomp, a new application currently in development for the Department of Energy's Building Energy Codes Program. CODEcomp uses a novel blending of search techniques to give users a powerful tool for searching and analyzing the content and topics of energy codes.
Web Searching with Visual Clues: A User Study BIBAPDF 35
  Ravee Malla; Monojit Choudhury; Kalika Bali
We present a user study where subjects are asked to solve fact-finding search tasks, where a visual clue is provided in addition to text. Search tasks with visual clues are often encountered in real life, for example when we come across an object, such as a flower or a landmark, that we would like to know more about. Our study reveals that these tasks are much harder to solve than the text-based ones, and users employ very different strategies for solving them. Furthermore, even though image search is extensively used to solve visual search tasks, there are several features that an ideal image search engine must possess before it can be effectively used for solving such tasks.
Supporting Inquiry by Design: Insights from a Study of Classroom-based Information InteractionEric Meyers BIBAPDF 36
 
Supporting student inquiry tasks in academic environments should be a priority for designers of Web search interfaces. These systems currently support fact-finding tasks well, but fall short in supporting inquiry activities that demand deeper conceptual understanding. This paper synthesizes results from recent research and draws on a school-based experimental study of students' inquiry practices to suggest several design moves for search result display. These moves, in conjunction with appropriate classroom interventions might move students from operationalist to conceptualist search strategies. The conceptualist search style was found to result in deeper information professing and better learning outcomes in middle school students.
WordSeer: Exploring Language Use in Literary Text BIBAPDF 37
  Aditi Muralidharan; Marti Hearst
Increasing numbers of primary and secondary source texts in the humanities have been digitized in recent years. Humanities scholars who want to study these new collections in depth need computational assistance because of their large scale. We have built WordSeer, a text analysis tool that includes visualizations and works on the grammatical structure of text extracted using highly accurate off-the shelf natural language processing tools. We have focused on the task of exploring language use patterns in a collection of North American slave narratives, but the technique is applicable to any text collection. Our preliminary user studies with humanities scholars show that WordSeer makes it easier for them to translate their questions into queries and find answers to their questions compared to a standard keyword-based search interface. In this paper, we present the system currently under development and describe text analysis features we plan to include in the next iteration.
Generating Hierarchical Virtual Directory by Metadata Frequency Difference BIBAPDF 38
  Mitsuharu Oba; Toshiko Matsumoto; Yasuaki Iwata; Takashi Onoyama
To achieve easy search and reuse of business documents stored in a file server, we propose a new clustering method to generate virtual directories implemented search conditions. Our method has three features; 1) Unified search viewpoint by clustering based on metadata, 2) Comprehensible virtual directory by keyword sequences, 3) Hierarchical virtual directory of appropriate granularity using frequency difference of keyword sequences. The experimental result demonstrates that our method achieved 97% precision and 86% recall. Moreover, our method was able to generate unexpected effective virtual directories.
A Taxonomy of Enterprise Search and Discovery BIBAPDF 39
  Tony Russell-Rose; Joe Lamantia; Mark Burrell
Classic IR (information retrieval) is predicated on the notion of users searching for information in order to satisfy a particular "information need". However, it is now accepted that much of what we recognize as search behaviour is often not informational per se. Broder (2002) has shown that the need underlying a given web search could in fact be navigational (e.g. to find a particular site) or transactional (e.g. through online shopping, social media, etc.). Similarly, Rose & Levinson (2004) have identified the consumption of online resources as a further common category of search behaviour.
   In this paper, we extend this work to the enterprise context, examining the needs and behaviours of individuals across a range of search and discovery scenarios within various types of enterprise. We present an initial taxonomy of "discovery modes", and discuss some initial implications for the design of more effective search and discovery platforms and tools.
Making Personal Retrieval Systems Comparable Using Self-Assigned Task Attributes BIBAPDF 40
  Seyedeh Sargol Sadeghi; Mark Sanderson; Falk Scholer
Evaluating Personal Search Systems is challenging due to the lack of common and shareable test collections in the personal context. Documents and search task requirements associated with this context are inherently personal and can vary widely among users. These characteristics make it difficult to gather documents and devise search tasks in order to build controllable test environments. This consequently leads to slow progress in the development of effective personal retrieval systems.
   In this position paper, we propose an approach to classifying search tasks based on their general attributes, which encourages users to classify the tasks themselves, as well as use tasks produced by others. To this end, we introduce a new model for the extraction of general task attributes which we call the Push-Pull Model. This approach can help to create comparable test environments across the tasks of different users. Furthermore, we highlight some of the key challenges for further investigation in this area.
Conditions of Trust for Completely-Remote Methods: A Proposal for Collaboration BIBAPDF 41
  Catherine L. Smith
Client-side logs are an important data source for research in HCIR. While methods for privacy protection are essential, and development continues on this front, an additional challenge remains. In order to collect client-side log data, volunteers must consent to participate in research; consent requires significant trust. For completely-remote methods, where volunteers download and install logging software, it is particularly difficult to establish the trustworthiness of a study. This paper proposes collaboration in a community of practice for remote methods, with emphasis on expressing the trustworthiness of our methods in a manner that can be understood by the public.
Interactive Evaluation of Interfaces for Story Tracking BIBAPDF 42
  Ilija Subasic; Bettina Berendt
Users often follow the same news story over an extended period of time and repeatedly search for the documents on the same topic (story tracking). In this paper we investigate how to evaluate document-search interfaces in this scenario. We first define a novel evaluation task and measures for interactive story tracking evaluation. Then, we present a study of four document-search interfaces based on graph and textual search functionality. The results of the study show that users slightly prefer the graph-based interfaces.
Social Navigation: A Position Paper BIBAPDF 43
  Daniel Tunkelang; Jonathan Koren; Paul Ogilvie; John Wang
In this position paper, we propose social navigation as a paradigm for information access. We define social navigation as navigation through explicit manipulation of a social lens and offer examples of its application.
A User Study on Improving the Effectiveness of a Spoken Language Interface to Information Systems BIBAPDF 44
  Xiaojun Yuan; Nicholas Belkin; Chris Jordan; Catherine Dumas
Research has shown that users of digital libraries and other information systems typically carry out searches with very short queries, on the order of two words or so. This makes it very difficult for the systems to disambiguate their queries and identify potentially relevant documents, resulting in sub-optimal retrieval performance. We hypothesize that users will provide better and more useful descriptions of their information problems if they are able to speak to the system and easily indicate through speech and gesture those documents and aspects of documents which they find useful, and not useful. In this paper, we introduced a spoken interface, and described a planned wizard of oz study.
Augmenting Conversations through Context-Aware Multimedia Retrieval based on Speech Recognition BIBAPDF 45
  Kamer Ali Yuksel; Aytul Ercil; Murat Celik Cansoy; Selim Balcisoy
Future's environments will be sensitive and responsive to the presence of people to support them carrying out their everyday life activities, tasks and rituals, in an easy and natural way. Such interactive spaces will use the information and communication technologies to bring the computation into the physical world, in order to enhance ordinary activities of their users. This paper describes a speech-based spoken multimedia retrieval system that can be used to present relevant video-podcast (vodcast) footage, in response to spontaneous speech and conversations during daily life activities. The proposed system allows users to search the spoken content of multimedia files rather than their associated meta-information and let them navigate to the right portion where queried words are spoken by facilitating within-medium searches of multimedia content through a bag-of-words approach. Finally, we have studied the proposed system on different scenarios by using vodcasts in English from various categories, as the targeted multimedia, and discussed how it would enhance people's everyday life activities by different scenarios including education, entertainment, marketing, news and workplace.
A Review of Search Interfaces in Consumer Health Websites BIBAPDF 46
  Yan Zhang
There is a surging interest among consumers to search for health and wellness-related information on the web. Many health websites have been developed to satisfy this interest. However, consumers are still frustrated by their search experience. To identify opportunities to improve the design of such websites, we reviewed the search interface of 18 representative consumer health websites. Design implications are discussed based on the results.