Developing methods for behavior scenario analysis (on the material of instructional texts)
Lists
Only you see this
Abstract
The article discusses the modeling of behavioral scenarios and methods for their extraction \nfrom texts published in social media. The authors proceed from the basic (in modern cognitive \nscience) position that the intentional aspect of a person’s behavior is reflected in his speech \nactivity. This gives reason to extract scenarios from the texts generated to carry out some \nactivity. The choice of instructive texts is determined by the fact that their genre, content and \ncommunicative intentions of their authors most explicitly represent the program of human \nbehavior. In this article we propose several methods for automatic construction of behavior \nscenarios, as well as a scenario model in the form of a frame. This model can be used in the \nsystem for automatic extraction of scenarios from texts and their further implementation. We \ndescribe an experiment on automatic scenario identification in texts and its results. The experiment \nincludes text segmentation after which each segment is associated with a particular \nstep of a scenario. Text segmentation involves dividing a text into semantic units, selecting the \nmost important of them, which express (by their lexical meaning and form) incentive modality, \nand finding some details to these units. In psychological terms, this means that we extract \nthose segments that contain description of some goals and particular actions that lead to their \nachievement. Reconstruction of the scenario in this case can be represented as automatic extraction \nof goals, actors, actions and conditions from selected segments. The result of text \nsegmentation achieves a fairly high F-measure.
BibTeX
@inproceedings{mishlanov2020developing,
author = {Valerii A. Mishlanov and Anfisa Chuganskaya and Ivan V. Smirnov and Margarita Suvorova and Ilya Kuruzov},
title = {{Developing methods for behavior scenario analysis (on the material of instructional texts)}},
booktitle = {Media},
year = {2020},
doi = {10.21638/spbu22.2020.102},
}Loading related content...