THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES RICARDO LAGE, PETER DOLOG, AND MARTIN LEGINUS

Slides:



Advertisements
Similar presentations
1 of 19 How to invest in Information for Development An Introduction IMARK How to invest in Information for Development An Introduction © FAO 2005.
Advertisements

Web Mining.
Project Proposal.
CS305: HCI in SW Development Evaluation (Return to…)
Learner Training Summer Training Outcomes Articulate how BloomBoard powers and streamlines the TESS evaluation process. Navigate the Learner Home.
Introduction Information Management systems are designed to retrieve information efficiently. Such systems typically provide an interface in which users.
Chapter 14: Usability testing and field studies. 2 FJK User-Centered Design and Development Instructor: Franz J. Kurfess Computer Science Dept.
Recommender Systems Aalap Kohojkar Yang Liu Zhan Shi March 31, 2008.
The use of a computerized automated feedback system Trevor Barker Dept. Computer Science.
Search Engines and Information Retrieval
Predicting Text Quality for Scientific Articles AAAI/SIGART-11 Doctoral Consortium Annie Louis : Louis A. and Nenkova A Automatically.
WebMiningResearch ASurvey Web Mining Research: A Survey Raymond Kosala and Hendrik Blockeel ACM SIGKDD, July 2000 Presented by Shan Huang, 4/24/2007.
The USE Project: Usability Evaluation and Software Design: Bridging the Gap University of Copenhagen Aalborg University Use Case Evaluation (UCE): A Method.
Enhanced Personalised Learning Support of Computer Algebra Systems Christian Gütl Institute of Information Systems and Computer Media (IICM), Graz University.
Designing Software for Personal Music Management and Access Frank Shipman & Konstantinos Meintanis Department of Computer Science Texas A&M University.
Agent Technology for e-Commerce
WebMiningResearchASurvey Web Mining Research: A Survey Raymond Kosala and Hendrik Blockeel ACM SIGKDD, July 2000 Presented by Shan Huang, 4/24/2007 Revised.
1 CS 430 / INFO 430 Information Retrieval Lecture 24 Usability 2.
Collaborative Filtering Shaun Kaasten CPSC CSCW.
ReQuest (Validating Semantic Searches) Norman Piedade de Noronha 16 th July, 2004.
U.C. Berkeley Calendar Network Usability Evaluation Nadine Fiebrich & Myra Liu IS214 May 4, 2004.
Recommender Systems; Social Information Filtering.
SIMS 213: User Interface Design & Development Marti Hearst Thurs, Jan 22, 2004.
Personalized Ontologies for Web Search and Caching Susan Gauch Information and Telecommunications Technology Center Electrical Engineering and Computer.
Evaluation in HCI Angela Kessell Oct. 13, Evaluation Heuristic Evaluation Measuring API Usability Methodology Matters: Doing Research in the Behavioral.
Semantic Web Technologies Lecture # 2 Faculty of Computer Science, IBA.
The 2nd International Conference of e-Learning and Distance Education, 21 to 23 February 2011, Riyadh, Saudi Arabia Prof. Dr. Torky Sultan Faculty of Computers.
Instructional Design Process Connect Your Website: Application Program Interfaces Jullien Gordon Aneto Okonkwo Gilbert Zaragoza.
Seeking and providing assistance while learning to use information systems Presenter: Han, Yi-Ti Adviser: Chen, Ming-Puu Date: Sep. 16, 2009 Babin, L.M.,
Search Engines and Information Retrieval Chapter 1.
Information Architecture The science of figuring out what you want your Web site to do and then constructing a blueprint before you dive in and put the.
Moodle (Course Management Systems). Blogs In this Lecture, we’ll cover how to use blogs, blog capablilities and efficive blog practices.
What does Public Policy ask of Complexity Science? Peter Dick Department of Health, UK Government ECCS ’12, Brussels, September 2012.
Interactive Probabilistic Search for GikiCLEF Ray R Larson School of Information University of California, Berkeley Ray R Larson School of Information.
Markup and Validation Agents in Vijjana – A Pragmatic model for Self- Organizing, Collaborative, Domain- Centric Knowledge Networks S. Devalapalli, R.
Information commitments, evaluative standards and information searching strategies in web-based learning evnironments Ying-Tien Wu & Chin-Chung Tsai Institute.
You Are What You Tag Yi-Ching Huang and Chia-Chuan Hung and Jane Yung-jen Hsu Department of Computer Science and Information Engineering Graduate Institute.
EXPLORING THE EFFECTIVENESS OF RCR EDUCATION IN THE SOCIAL AND BEHAVIORAL SCIENCES Jim Vander Putten Department of Educational Leadership Amanda L. Nolen.
The Structure of Information Retrieval Systems LBSC 708A/CMSC 838L Douglas W. Oard and Philip Resnik Session 1: September 4, 2001.
S&I Provider Directories Initiative Revisions to Initiative Charter July 1, 2011.
AnnotatEd: A Social Navigation and Annotation Service for Web-based Educational Resources Rosta Farzan & Peter Brusilovsky Personalized Adaptive Web Systems.
Knowledge Base on Economic Statistics and Macroeconomic Standards Annette Becker, UNSD.
Digital Learning India 2008 July , 2008 Mrs. C. Vijayalakshmi Department of Computer science and Engineering Indian Institute of Technology – IIT.
1 Adaptive Subjective Triggers for Opinionated Document Retrieval (WSDM 09’) Kazuhiro Seki, Kuniaki Uehara Date: 11/02/09 Speaker: Hsu, Yu-Wen Advisor:
Peter Brusilovsky. Index What is adaptive navigation support? History behind adaptive navigation support Adaptation technologies that provide adaptive.
Unit 8: Implementation, Part II Seminar Wednesday pm ET.
Adaptive Faceted Browsing in Job Offers Danielle H. Lee
Identifying, Evaluating and Prioritising Urban Adaptation Measures.
Introduction to Blackboard Rabie A. Ramadan Session 3.
Academic Writing Skills: Paraphrasing and Summarising Activities and strategies to help students.
INFORMATION RETRIEVAL MEASUREMENT OF RELEVANCE EFFECTIVENESS 1Adrienn Skrop.
Present apply review Introduce students to a new topic by giving them a set of documents using a variety of formats (e.g. text, video, web link etc.) outlining.
Adaptivity, Personalisation and Assistive Technologies Hugh Davis.
Using Blog Properties to Improve Retrieval Gilad Mishne (ICWSM 2007)
Lecture-6 Bscshelp.com. Todays Lecture  Which Kinds of Applications Are Targeted?  Business intelligence  Search engines.
Ten Usability Heuristics These are ten general principles for user interface design. They are called "heuristics" because they are more in the nature of.
Evaluation of an Information System in an Information Seeking Process Lena Blomgren, Helena Vallo and Katriina Byström The Swedish School of Library and.
Objectives Explain the term “Balanced Counseling Strategy (BCS) Plus”
Information Storage and Retrieval Fall Lecture 1: Introduction and History.
Objectives Explain the term “Balanced Counseling Strategy (BCS) Plus”
Augmenting (personal) IR
P7: Annotated Wireframes
Martin Rajman, EPFL Switzerland & Martin Vesely, CERN Switzerland
Usability Techniques Lecture 13.
Tasks & Grades for MET1.
Panagiotis G. Ipeirotis Luis Gravano
Kasper Hornbæk Department of Computer Science University of Copenhagen
Analyzing and Organizing Information
WSExpress: A QoS-Aware Search Engine for Web Services
Presentation transcript:

THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES RICARDO LAGE, PETER DOLOG, AND MARTIN LEGINUS

Motivation Task Evaluation Set Up Initial System GUI Evaluation Resutls New System GUI Results Conlusions Outline THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGENT WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

Task of epidemic surveilence Monitoring official sources Monitoring social media not so common Support for exploring a large number of indications and signals Signals – aggregates of information items (tweets, messages, …) with number over certain treshold There are only very few studies of user interfaces in general and no adaptive user interfaces in particular Motivation THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

Build a system which supports a survailance on social media Evaluate the system with experts Based on evaluation build an improved version Evaluate in the second round Context: Meco FP7 EU project Task THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

Health Map: Interesting system, no data on UI or filtering studies Real Time Outbreak and Disease Surveilance Focusing on official sources, study of use not known to us Other domains News recoomendation: slightly different task – news aggregations are usually not urgent, they do not have to be monitored continuosly, … Notifications and awareness: task can be very different, but awareness is also our focus => we take on a strategy where users are drivers Visualization: for example trendig topics and topic flow on twitter => different task, requires different focus for visualization Related work THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

Focus group A small group – 6-12 people Shared understanding while a possibility to voice different opinions Moderator to ensure to stay within predefined topics Our method: 2 rounds – after the initial prototype and after the changes from the first round Evaluation method THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

Rating scale to assess quality or quantity Thumbs up or thumbs down Bookmarking Comments Elements considered THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

8 participants – survailence experts/representatives of international epidemics organizations Asked to create signales of their interests The system then produced recommendations After they have browsed the recommended signals and documents we have conducted the focus group with these questions: How would recommendations help you deal with the excess of information you might receive? How would you like to evaluate the recommendations you receive? How should the recommendations be placed in the system? Discussion took one and half hour Goal: to discuss and learn how to present recommendations in the surveilence task Evaluation set-up: Focus Group THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

Initial Prototype/Signal Definition THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

Initial Prototype/Signals and Documents THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

Initial Prototype/Navigation THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

Useful: Tag cloud useful Rating of signals important To improve: Search process Information they provided Content organization Users should be able to assign new tags Relevancy and irrelevancy of tags should be exposed Results THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

Q1: The system advises them about missing information – help them to discover topics relevant to their interest, not exact match Q1: Recommendations help in overload Q2: Agreed on usefulness of signal evaluations Q2: Same options as for signal evaluation should be available also for documents Q2: Options for re-ranking should be available Q2: Dislike option should be available Q3: Recommendation or recommended signal as a term is not very appropriate; instead ”related signals” could be used => they would like to know reason for recommendations Answers to questions THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

New GUI/Map THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

New GUI/Signal Listing THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

1. the user rules and the contents of each signal’s documents; 2. the user rules and the properties (i.e., disease and location values) of each signal; 3. the user’s specific rules for locations, similar locations and each signal’s documents; 4. the user’s specific rules for locations, similar locations and the locations together with similar locations of each signal; 5. the tag set of the user and the contents of each signal’s documents; 6. the tag set of the user and the properties of each signal; 7. the date of the signal and the date when the recommendation is being computed. Explanation based on the highest score in four categories: content (1,2), location (3,4), tag (5, 6), and date (7) Factors in similarity calculations THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

New GUI/Tag cloud THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

The same participants All rated the changes possitively More tabs for example with a timeline Tag cloud provides additional context to the list of signal Tag cloud simplifies the browsing process 2nd Focus Group THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET

Visualization of recommendations and specification of preferences is at least as important as algorithms for recommendations Content organization, possibilities for implicit feedback, explanations are all means which improve the percieved recommendations Focus group with experts is a good method to conduct evaluations to receive both: confirmations for the design but also suggestions for changes Conclusions THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES – 9. JULY 2014 INTELLINGET WEB AND INFORMATION SYSTEMS, DEPARTMENT OF COMPUTER SCIENCE AALBORG UNIVERSITET