Predicting Sequences of User Actions
Published 1 January 1998
Brian D. Davison, Haym Hirsh
Citations185
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Characteristics of an idealized algorithm that, when applied to sequences of user actions, would allow a user interface to adapt over time to an individual’s pattern of use are proposed.
Abstract
AAAI/ICML 1998 Workshop on Predicting the Future: AI Approaches to Time-Series Analysis 1 People display regularities in almost everything they do. This paper proposes characteristics of an idealized algorithm that, when applied to sequences of user actions, would allow a user interface to adapt over time to an individual’s pattern of use. We describe a simple predictive method with these characteristics and show its predictive accuracy on a large dataset of UNIX commands to be at least as good as others that have been considered, while using fewer computational and memory resources.
Keywords
Computer Science
C4.5: Programs for Machine Learning
23,665 Citations1992J. R. Quinlan
A complete guide to the C4.5 system as implemented in C for the UNIX environment, which starts from simple core learning methods and shows how they can be elaborated and extended to deal with typical problems such as missing data and over hitting.
Communications of the ACMAgents that reduce work and information overload
2,321 Citations1994Pattie Maes
Results from several prototype agents that have been built using an approach to building interface agents are presented, including agents that provide personalized assistance with meeting scheduling, email handling, electronic news filtering, and selection of entertainment.
Watch what I do: programming by demonstration
1,024 Citations1993Allen Cypher, Daniel C. Halbert +5 more
Part 1 Systems: Pygmalion tinker a predictive calculator rehearsal world smallStar peridot metamouse TELS eager garnet the Turvy experience chimera the geometer's sketchpad tourmaline a history-based macro by example system mondrian triggers the AIDE project.
Machine LearningIncremental Induction of Decision Trees
790 Citations1989Paul E. Utgoff
An incremental algorithm for inducing decision trees equivalent to those formed by Quinlan's nonincremental ID3 algorithm, given the same training instances is presented, named ID5R.
Web Watcher: A Tour Guide for the World Wide Web.
681 Citations1997Thorsten Joachims, Dayne Freitag +1 more
The learning algorithms used by WebWatcher, experimental results showing their e ectiveness, and lessons learned from this case study in Web tour guide agents are described.
International Journal of Human-Computer StudiesHow people revisit web pages: empirical findings and implications for the design of history systems
563 Citations1997Linda Tauscher, Saul Greenberg
Based on users' revisitation patterns to World Wide Web pages, eight design guidelines for web browser history mechanisms were formulated and explain why some aspects of today's browsers seem to work well, and other's poorly.
Purdue e-Pubs (Purdue University)Classification and detection of computer intrusions
382 Citations1996Sandeep Kumar
This document summarizes current capabilities, research and operational priorities, and plans for further studies that were established at the 2015 USGS workshop on quantitative hazard assessments of earthquake-triggered landsliding and liquefaction in the western hemisphere.
International Joint Conference on Artificial IntelligenceLEAP: a learning apprentice for VLSI design
249 Citations1985Tom M. Mitchell, Sridhar Mahadevan +1 more
Learning interface agents
241 Citations1993Pattie Maes, Robyn Kozierok
It is argued that the machine learning approach to building interface agents is a feasible one which has several advantages over other approaches: it provides a customized and adaptive solution which is less costly and ensures better user acceptability.
Evolving agents for personalized information filtering
227 Citations2002B. Sheth, Pattie Maes
Results of a set of experiments are presented in which a small population of information filtering agents was evolved to make a personalized selection of news articles from the USENET newsgroups, showing that the artificial evolution component of the system is responsible for improving the recall rate of the selected set of articles, while learning from feedback component improves the precision rate.
ComputerThe Reactive Keyboard: a predictive typing aid
178 Citations1990John J. Darragh, Ian H. Witten +1 more
The Reactive Keyboard, a device that accelerates typewritten communication with a computer system by predicting what the user is going to type next is described, and it requires no physical keyboard.
PRISM (University of Calgary)USING UNIX: COLLECTED TRACES OF 168 USERS
119 Citations1988Saul Greenberg
Communications of the ACMGenerating text from compressed input
103 Citations1992Patrick Demasco, Kathleen F. McCoy
While the standard computer keyboard is an efficient interface for able-bodied people and some disabled people, it may present significant access problems for others, in these cases some alternative interface is necessary.
A sound and fast goal recognizer
85 Citations1995Neal Lesh, Oren Etzioni
This work describes a goal recognition module that is provably sound and polynomial-time and that performs well in a real domain and reports on experiments on human subjects in the Unix domain that demonstrate the algorithm to be fast in practice.
Inferring Sequential Structure
78 Citations1996Craig G. Nevill-Manning
Simple, robust techniques are developed that reveal interesting structure in a wide range of real-world sequences including music, English text, descriptions of plants, graphical figures, DNA sequences, word classes in language, a genealogical database, programming languages, execution traces, and diverse sequences from a data compression corpus.
Machine LearningDiscrete Sequence Prediction and Its Applications
68 Citations1994Philip Laird, Ronald Saul
This work presents a simple and practical algorithm (TDAG) for discrete sequence prediction based on a text-compression method that limits the growth of storage by retaining the most likely prediction contexts and discarding less likely ones.
The Computer User as Toolsmith: The Use, Reuse and Organization of Computer-Based Tools
60 Citations1993Saul Greenberg
A workspace system: description and issues and techniques for reusing activities through workspaces, which show the importance of knowing how to reuse activities.
IEEE ExpertA machine-learning apprentice for the completion of repetitive forms
54 Citations1994L.A. Hermens, J.C. Shlimmer
Investigations into history tools for user support
34 Citations1992Allison Lee
This dissertation investigates the prospects for history based, user support tools, and proposes several kinds of history information and history functions that need to be supported in new designs of history tools integrating all seven uses of history.
Repeat and predict—two keys to efficient text editing
33 Citations1994Toshiyuki Masui, Ken Nakayama
Although being simple, a wide range of repetitive tasks can be performed just by typing the repeat key, and when the authors use another special “pre-dict” key for conventional prediction techniques in addition to the repeat key, wider range of prediction schemes can be performed depending on the order of using these two keys.
Toward an adaptive command line interface
29 Citations1997Brian D. Davison, Haym Hirsh
This paper explores different mechanisms for predicting the next command to be used for the UNIX command-line shell, and has calculated the predictive accuracy for each of five method over this dataset.
Adaptive goal recognition
23 Citations1997Neal Lesh
Adapt is constructed, a recognizer-independent unsupervised-learning algorithm for adapting a Recognizer to a person's idiosyncratic behaviors and shows that applying Adapt to the BOCE recognizer can improve its performance by a factor of two to three.
An adaptive short list for documents on the World Wide Web
19 Citations1997Matjaž Debevc, Beth Meyer +1 more
The goal of this system is to determine the most appropriatesites to include in the Adaptive Short List based on usagedata which the system collects and analyzes while the userworks, to enable users to check the most probablesites quickly.
International Journal of Human-Computer InteractionAutomated user modeling for intelligent interface
17 Citations1996Kenichi Yoshida, Hiroshi Motoda
A new framework is presented that analyzes the computational processes activated by the user commands to build the user behavior model and a user-adaptive interface system, CHpBoard, was developed to show the adequacy of this framework.
Artificial IntelligenceMachine learning techniques to make computers easier to use
17 Citations1998Hiroshi Motoda, Kenichi Yoshida
The results clearly shows that the dependency analysis of computational processes activated by the user commands which is made possible by GBI is indeed useful to build a behavior model and increase prediction accuracy.
National Conference on Artificial IntelligenceExperiments in UNIX command prediction
16 Citations1997Brian D. Davison, Haym Hirsch
The task of modifying a UNIX shell to learn to predict the next command executed as one sample adaptive user interface is considered and the predictive accuracy for each of the methods calculated.
Journal of Artificial Intelligence ResearchQuantitative Results Comparing Three Intelligent Interfaces forInformation Capture: A Case Study Adding Name Information into a
11 Citations1996Jeffrey C. Schlimmer, P. C. Wells
Three intelligent user interfaces are described: handwriting recognition, adaptive menus, and predictive fillin in the context of adding a person's name and address to an electronic organizer, which shows handwriting recognition is slower than typing on an on-screen, soft keyboard, while adaptive menus and predictive Fillin can be twice as fast.
User command prediction by graph-based induction
9 Citations2002Kenichi Yoshida
A new framework is presented that overcomes this limitation and demonstrates its power experimentally the relationship between the user commands.
Lecture notes in computer scienceEvidential reasoning in network intrusion detection systems
8 Citations1996Mansour Esmaili, Reihaneh Safavi–Naini +1 more
It is shown how dealing with uncertainty can allow the system to detect the abnormality in the user behavior more efficiently and be able to deal with uncertainty in Intrusion Detection Systems.