Educational support in a video tagging game

About Educational support in a video tagging game

• Contact person: has supervisor::Lora Aroyo

• This project has not yet been fulfilled.
• This project fits in the following Bachelor programs: {{#arraymap:|, |xXx|bachelorproject within::xXx|,}}
• This project fits in the following masterareas: {{#arraymap:Multimedia, Internet and Web Technology, Knowledge Technology and Intelligent Internet Applications, Information Sciences|, |xXx|project within::xXx|,}}

Description

Waisda is a video labeling game from the VU and the Netherlands Institute for Sound and Vision. In this game users score points by entering tags for a video. Typically, the tags that users enter describe what you can see and hear in the video. In this project you investigate how users can be taught to provide more in-depth descriptions. For example, in the movie domain we can distinguish categories, such as:

• Factual. What you see or hear in the scene, such as objects, persons, places and actions (e.g. woman, sofa, London, R2D2, murder).
• Cinematographic. Stylistic features, such as form, style, framing, camera movement, lightning key, type of shot, camera angle (e.g. backlighting, wide-angle, close-up, fade-out, caligarism).
• Explanatory. Symbolic interpretation of the meaning or theme (e.g. psychotic rage, oppression, dehumanization).
• Emotional. The emotions, thoughts or intentions of the characters (e.g. bored, happiness, despair) or your own emotions (e.g. boring, fascinating).

A possible approach is to create multiple levels in Waisda.

• At the basic level users are instructed about the different categories
• At the medium level users have to show that they can apply the tags from different categories appropriately
• At the expert level users can teach or judge basic or medium level users

Tasks

• study literature on crowdsourcing, games-with-a-purpose, video tagging/annotation and movie theory
• extend Waisda with basic support for levels
• collected feedback from experts and users
• evaluate the experiences with the application and/or the quality of the collected data

Tools, Data, Technologies

Tools

• Waisda white label

Possible video collections

• Videos from the EYE film institute Netherlands
• Videos from the Netherlands Institute for Sound and Vision

Possible technologies

• HTML5/JavaScript
• Java (Spring Framework)
• MySQL

Recommended prior knowledge

• Web technology
• Multimedia authoring
• Research methods

Extra Information

Contact Michiel_Hildebrand for more information about this project.