Summary of the paper
| Title | A Language Approach to Modeling Human Behaviors |
|---|---|
| Authors | Peng-Wen Chen, Snehal Kumar Chennuru and Ying Zhang |
| Abstract | The modeling of human behavior becomes more and more important due to theincreasing popularity of context-aware computing and people-centric mobileapplications. Inspired by the principle of action-as-language, we propose thathuman ambulatory behavior shares similar properties as natural languages. Inaddition, by exploiting this similarity, we will be able to index, recognize,cluster, retrieve, and infer high-level semantic meanings of human behaviorsvia the use of natural language processing techniques. In this paper, wedeveloped a Life Logger system to help build the behavior language corpus whichsupports our "Behavior as Language" research. The constructed behavior corpusshows Zipf's distribution over the frequency of vocabularies which is alignedwith our "Behavior as Language" assumption. Our preliminary results of usingsmoothed n-gram language model for activity recognition achieved an averageaccuracy rate of 94% in distinguishing among human ambulatory behaviorsincluding walking, running, and cycling. This behavior-as-language corpus willenable researchers to study higher level human behavior based on the syntacticand semantic analysis of the corpus data. |
| Language | Statistical and machine learning methods |
| Topics | Corpus (creation, annotation, etc.), Language modelling, Statistical and machine learning methods |
Full paper  |
A Language Approach to Modeling Human Behaviors |
| Bibtex | @InProceedings{CHEN10.580, author = {Peng-Wen Chen, Snehal Kumar Chennuru and Ying Zhang}, title = {A Language Approach to Modeling Human Behaviors}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |