Intention mining: surfacing and reshaping deep intentions by proactive human computer interaction

Date

2024-12

Author

Şencan, Cevdet

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

85
views

113
downloads

Cite This

In this study, we contribute to intention mining and reshaping with an HCI equipped with our Intention Risk and Stimulus factor Impact (IRSI) approach that enables to carry out the reshaping of the intention by taking into account the shape and color condition of proactive visuals that determine the emotional interaction of the robotic proactive stimulus, the risk status of intention matched with human intentional moves and the habituation status of the human, subject to a stimulus provided by the robotic system. More specifically our mining and reshaping system within HCI comprises of two phases: the recognition of deep intention surfacing by HCI (intention mining) and the reshaping of this deep intention into a non-premeditated, newly fabricated one by our system. As a demonstrative experimental setup for our system, we adapt the bluff card game played face-to-face with a computer interface that helps mine and reshape intentions of the players. In order to generate a model verification of our system, actual bluff game sessions which contain different risks are registered and analyzed, and bluff moves are labeled through the generation of intention matrices. Afterwards, intention recognition is performed on test videos where a CNN-based deep learning method has been previously applied and our system learns bluff human moves. In the last stage, the intentional moves of the players confront appropriate proactive stimuli by our robotic system, adapting to different risk levels in order to psychologically affect the current intentions that surface for the player during his/her move and reshape it into a desired new intention that is not among the natural intention of the current player. Here, a computer robotic interface we designed provides visuals as proactive stimuli using the psychobiological emotional effect of shape and color depending on the risk taking and habituation factor on the player. The efficiency of our intention mining for reshaping HCI system has been experimentally demonstrated and the intention reshaping performance of our computer interface is analyzed based on these psychobiological parameters of our system.

Subject Keywords

Intention risk and stimulus factor impact (IRSI), Human intention reshaping, Human-computer interaction, Intention recognition

URI

https://hdl.handle.net/11511/112941

Collections

Graduate School of Natural and Applied Sciences, Thesis