Predicting Future User Actions by Observing Unimodified Applications

Predicting Future User Actions by Observing Unimodified Applications. Gorniak, P. & Poole, D. In Conference of the American Association for Artificial Intelligence, 2000.
abstract bibtex

Intelligent user interfaces often rely on modiﬁed applica- tions and detailed application models. Such modiﬁcations and models are expensive to build and maintain. We pro- pose to automatically model the use of unmodiﬁed applica- tions to solve this problem. We observe a user’s interactions with the application’s interface and from these observations infer a state space which the user navigates and the stochas- tic policy he or she follows. ONISI, the algorithm presented here, builds this state space implicitly and on-line, and uses it to predict future user actions. Trials with real users show that this algorithm predicts the next user action signiﬁcantly better than another current algorithm.

@InProceedings{ 5021,
	author = "P. Gorniak and D. Poole",
	title = "Predicting Future User Actions by Observing Unimodified Applications",
	booktitle = "Conference of the American Association for Artificial Intelligence",
	year = "2000",
	abstract = "Intelligent user interfaces often rely on modiﬁed applica- tions and detailed application models. Such modiﬁcations and models are expensive to build and maintain. We pro- pose to automatically model the use of unmodiﬁed applica- tions to solve this problem. We observe a user’s interactions with the application’s interface and from these observations infer a state space which the user navigates and the stochas- tic policy he or she follows. ONISI, the algorithm presented here, builds this state space implicitly and on-line, and uses it to predict future user actions. Trials with real users show that this algorithm predicts the next user action signiﬁcantly better than another current algorithm. ",
	localfile = "/home/stephan/Daten/Arbeit/Paper\_Tutorials/Paper/000101\_5021\_PredictingFutureUserActionsbyObservingUnmodifiedApplications\_PGorniak-aaai-2000-p1.pdf"
}

Downloads: 0

{"_id":"smyynMbu6jQWFZB6i","bibbaseid":"gorniak-poole-predictingfutureuseractionsbyobservingunimodifiedapplications-2000","downloads":0,"creationDate":"2016-04-30T08:54:33.861Z","title":"Predicting Future User Actions by Observing Unimodified Applications","author_short":["Gorniak, P.","Poole, D."],"year":2000,"bibtype":"inproceedings","biburl":"http://www.stephansigg.de/stephan/AmbientIntelligenceGroup/bibtex/LiteraturStephan","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["P."],"propositions":[],"lastnames":["Gorniak"],"suffixes":[]},{"firstnames":["D."],"propositions":[],"lastnames":["Poole"],"suffixes":[]}],"title":"Predicting Future User Actions by Observing Unimodified Applications","booktitle":"Conference of the American Association for Artificial Intelligence","year":"2000","abstract":"Intelligent user interfaces often rely on modiﬁed applica- tions and detailed application models. Such modiﬁcations and models are expensive to build and maintain. We pro- pose to automatically model the use of unmodiﬁed applica- tions to solve this problem. We observe a user’s interactions with the application’s interface and from these observations infer a state space which the user navigates and the stochas- tic policy he or she follows. ONISI, the algorithm presented here, builds this state space implicitly and on-line, and uses it to predict future user actions. Trials with real users show that this algorithm predicts the next user action signiﬁcantly better than another current algorithm. ","localfile":"/home/stephan/Daten/Arbeit/Paper_Tutorials/Paper/000101_5021_PredictingFutureUserActionsbyObservingUnmodifiedApplications_PGorniak-aaai-2000-p1.pdf","bibtex":"@InProceedings{ 5021,\n\tauthor = \"P. Gorniak and D. Poole\",\n\ttitle = \"Predicting Future User Actions by Observing Unimodified Applications\",\n\tbooktitle = \"Conference of the American Association for Artificial Intelligence\",\n\tyear = \"2000\",\n\tabstract = \"Intelligent user interfaces often rely on modiﬁed applica- tions and detailed application models. Such modiﬁcations and models are expensive to build and maintain. We pro- pose to automatically model the use of unmodiﬁed applica- tions to solve this problem. We observe a user’s interactions with the application’s interface and from these observations infer a state space which the user navigates and the stochas- tic policy he or she follows. ONISI, the algorithm presented here, builds this state space implicitly and on-line, and uses it to predict future user actions. Trials with real users show that this algorithm predicts the next user action signiﬁcantly better than another current algorithm. \",\n\tlocalfile = \"/home/stephan/Daten/Arbeit/Paper\\_Tutorials/Paper/000101\\_5021\\_PredictingFutureUserActionsbyObservingUnmodifiedApplications\\_PGorniak-aaai-2000-p1.pdf\"\n}\n\n","author_short":["Gorniak, P.","Poole, D."],"key":"5021","id":"5021","bibbaseid":"gorniak-poole-predictingfutureuseractionsbyobservingunimodifiedapplications-2000","role":"author","urls":{},"downloads":0,"html":""},"search_terms":["predicting","future","user","actions","observing","unimodified","applications","gorniak","poole"],"keywords":[],"authorIDs":[],"dataSources":["LHPT6ZANm8yTecwp8"]}