Digging out implicit semantics from user interaction

Abstract

User interaction may take many forms in multimedia systems. Current systems mainly waste this implicit and natural source of semantic knowledge and rather create tedious and unnatural interaction protocols.
We advocate for a complete integration of natural interaction protocols and semantic knowledge capture, mainly thru mining interaction sessions. 
We assert that users possess the ability to quickly examine and summarise these documents, even subconsciously. Examples include specifying relevance between a query and results, rating preferences in film databases, purchasing items from online retailers, and even simply browsing web sites. Data from these interactions, captured and stored in log files, can be interpreted to have semantic meaning, which proves indispensable when used in a collaborative setting where users share similar preferences and goals.