Building an Aviation Corpus Conclusions & Future Work BUILDING AN LSA-SIMULATED REPRESENTATION OF PILOT AVIATION KNOWLEDGE Accelerating Development of.

Slides:



Advertisements
Similar presentations
Bayesian tools for analysing and reducing uncertainty Tony OHagan University of Sheffield.
Advertisements

Map of Human Computer Interaction
The Chinese Room: Understanding and Correcting Machine Translation This work has been supported by NSF Grants IIS Solution: The Chinese Room Conclusions.
Chapter 11 user support. Issues –different types of support at different times –implementation and presentation both important –all need careful design.
Chapter 4 Design Approaches and Methods
Blackmon, Kitajima, & Polson, CHI2005 1/26 Tool for Accurately Predicting Website Navigation Problems, Non-Problems, Problem Severity, and Effectiveness.
The Cognitive Walkthrough and Cognitive Walkthrough for the Web -- A Worked Example (Computer Mediated Communication) (René van der Ark) (RuG)
A general-purpose text annotation tool called Knowtator is presented. Knowtator facilitates the manual creation of annotated corpora that can be used for.
1 / 22 Issues in Text Similarity and Categorization Jordan Smith – MUMT 611 – 27 March 2008.
Ch 11 Cognitive Walkthroughs and Heuristic Evaluation Yonglei Tao School of Computing and Info Systems GVSU.
Software Testing and Quality Assurance
CAP 252 Lecture Topic: Requirement Analysis Class Exercise: Use Cases.
Class 6 LBSC 690 Information Technology Human Computer Interaction and Usability.
Measuring the quality of academic library electronic services and resources Jillian R Griffiths Research Associate CERLIM – Centre for Research in Library.
Today’s class Group Presentation More about principles, guidelines, style guides and standards In-class exercises More about usability Norman’s model of.
Providing Tutoring Service through Accumulating Interaction Data Chi-Jen LIN Fo Guang University, Taiwan.
Lecture Fourteen Methodology - Conceptual Database Design
Overview of Software Requirements
1 User Centered Design and Evaluation. 2 Overview My evaluation experience Why involve users at all? What is a user-centered approach? Evaluation strategies.
Latent Semantic Analysis (LSA). Introduction to LSA Learning Model Uses Singular Value Decomposition (SVD) to simulate human learning of word and passage.
Mr. Perminous KAHOME, University of Nairobi, Nairobi, Kenya. Dr. Elisha T.O. OPIYO, SCI, University of Nairobi, Nairobi, Kenya. Prof. William OKELLO-ODONGO,
Usability Teppo Räisänen
Task analysis 1 © Copyright De Montfort University 1998 All Rights Reserved Task Analysis Preece et al Chapter 7.
Information Systems Development : Overview. Information systems development practice Concept and role of a systems development methodology Approaches.
Semantic Web Technologies Lecture # 2 Faculty of Computer Science, IBA.
1. Learning Outcomes At the end of this lecture, you should be able to: –Define the term “Usability Engineering” –Describe the various steps involved.
1. Human – the end-user of a program – the others in the organization Computer – the machine the program runs on – often split between clients & servers.
Using Provenance to Support Real-Time Collaborative Design of Workflows Tommy Ellkvist 1, Erik Anderson 2, David Koop 2, Juliana Freire 2, and Claudio.
Unit 2: Engineering Design Process Foundations of Technology Lesson 3: Design Principles Design Principles.
1 Usability evaluation and testing User interfaces Jaana Holvikivi Metropolia.
INDEXING A good index combines intelligence with user language to create lookup terms The first task is to scope the pieces of information – a list of.
Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification on Reviews Peter D. Turney Institute for Information Technology National.
Copyright R. Weber Machine Learning, Data Mining ISYS370 Dr. R. Weber.
Chapter 8 Architecture Analysis. 8 – Architecture Analysis 8.1 Analysis Techniques 8.2 Quantitative Analysis  Performance Views  Performance.
IST Conference Paper Prototyping a Dynamic Software Interface: A Case Study Using APT Andrew Barrett Jamison Judd.
Usability Evaluation Yogi
Overview of the rest of the semester Building on Assignment 1 Using iterative prototyping.
Chapter 10 Information Systems Analysis and Design
Overview of the rest of the semester Iteratively design interface to help people log their food intake over the long term.
Chapter 3: Managing Design Processes
Implicit Acquisition of Context for Personalization of Information Retrieval Systems Chang Liu, Nicholas J. Belkin School of Communication and Information.
Human Computer Interaction
Extended Cognitive Walkthrough Judy Kay CHAI: Computer human adapted interaction research group School of Information Technologies.
Methodology - Conceptual Database Design
User Support Chapter 8. Overview Assumption/IDEALLY: If a system is properly design, it should be completely of ease to use, thus user will require little.
CS2003 Usability Engineering Human-Centred Design Dr Steve Love.
CONCLUSION & FUTURE WORK Normally, users perform search tasks using multiple applications in concert: a search engine interface presents lists of potentially.
Benchmarking ontology-based annotation tools for the Semantic Web Diana Maynard University of Sheffield, UK.
1 Chapter 3 1.Quality Management, 2.Software Cost Estimation 3.Process Improvement.
Computer Concepts 2014 Chapter 10 Information Systems Analysis and Design.
Chap#11 What is User Support?
Project Database Handler The Project Database Handler is a brokering application that mediates interactions between the project database and the external.
Requirements Validation
OOPSLA workshop on Domain-Specific Visual Languages 1 Juha-Pekka Tolvanen, Steven Kelly, Jeff Gray, Kalle Lyytinen.
Link Distribution on Wikipedia [0407]KwangHee Park.
Virtual Examples for Text Classification with Support Vector Machines Manabu Sassano Proceedings of the 2003 Conference on Emprical Methods in Natural.
1 Usability evaluation and testing User interfaces Jaana Holvikivi Metropolia.
Be.wi-ol.de User-friendly ontology design Nikolai Dahlem Universität Oldenburg.
TRAINING PACKAGE The User Action Framework Reliability Study July 1999.
5. 2Object-Oriented Analysis and Design with the Unified Process Objectives  Describe the activities of the requirements discipline  Describe the difference.
ASSESSING SEARCH TERM STRENGTH IN SPOKEN TERM DETECTION Amir Harati and Joseph Picone Institute for Signal and Information Processing, Temple University.
Interaction Frameworks COMPSCI 345 S1 C and SoftEng 350 S1 C Lecture 3 Chapter (Heim)
Chapter 11 user support. Overview Users require different types of support at different times. There are four main types of assistance that users require:
What Do We Mean by Usability?
INCOSE Usability Working Group
HI 5354 – Cognitive Engineering
Program comprehension during Software maintenance and evolution Armeliese von Mayrhauser , A. Marie Vans Colorado State University Summary By- Fardina.
CSc4730/6730 Scientific Visualization
Usability Techniques Lecture 13.
Chapter 11 user support.
Presentation transcript:

Building an Aviation Corpus Conclusions & Future Work BUILDING AN LSA-SIMULATED REPRESENTATION OF PILOT AVIATION KNOWLEDGE Accelerating Development of NextGen with Affordable Task Analysis Tools Marilyn Blackmon (Ph.D.), Peter Polson (Ph.D.), Lance Sherry (Ph.D.), & Michael Feary (Ph.D.) University of Colorado, George Mason University, NASA – Ames Research Center Accurately predict probability-of-failure-to-complete for both routine and infrequently performed, safety-critical tasks; also predict depth/familiarity of underlying concepts Test whether infrequently performed, safety-critical tasks will be semantically salient and intuitive to prevent errors Identify usability problems in a design early in the design cycle Can also be used to evaluate training designs Context Research Approach LSA-simulated Pilot Aviation Knowledge Problem Statement Affordable Operator Performance Models require a representation of the aviation knowledge of pilots — an Aviation Corpus — to evaluate proposed systems being incorporated into NextGen automation An Aviation Corpus is a collection of all the texts that pilots have read about aviation at a particular level of pilot expertise. It can be “read” by Latent Semantic Analysis (LSA) or other language models (e.g., PMI-IR) Requirements: – –Combined with the performance model, the corpus can be used to simulate pilots doing any specific task, predicting whether pilots will do the task correctly, rapidly, and safely or be prone to errors – –The simulation of pilot aviation knowledge can be incorporated into other task analysis tools (ADEPT, HCIPA, CogTool, SNIF-ACT) Latent Semantic Analysis (LSA) “reads” the Aviation Corpus — text files of all key documents pilots have read — and builds a valid computer-simulated representation of pilots’ aviation knowledge — expert aviation knowledge pilots gained from reading these texts LSA is a well-established computational model of language that can represent any knowledge domain LSA provides automated, objective measures of semantic similarity, word frequency, and concept depth/familiarity – –Blackmon, Polson, et al. (2005, 2007) developed an automated usability evaluation tool called CWW that synthesizes multiple measures — semantic similarity, concept familiarity, attention — to accurately predict task performance of a particular user group – –CWW is especially accurate at identifying and repairing serious usability problems — where probability-of-failure-to-complete a task is 25% to 75% or more Generalize lessons learned from CWW research to evaluating usability of NextGen automation By analogy to CWW, we will use the LSA-simulated pilot knowledge to make accurate predictions synthesizing three measures: Will the pilot focus on the correct subregion of the display? Will the correct action be the most salient option, the one most semantically similar to the goal and thus most apt to be chosen? Will selection of the correct action be less likely due to conceptual unfamiliarity (insufficient knowledge or infrequent use)? Join computational model that represents pilots’ aviation knowledge with proven tool called CWW Figure at left: Blackmon et al. (2007) verified that using the CWW tool with LSA accurately predicts which tasks will be easy, medium, and hard and successfully repairs tasks that are hard. The Aviation Knowledge Corpus, once built, will have many potential uses for a wide variety of aviation research projects LSA-simulated Pilot Aviation Knowledge