Linguamix sessions collect rich student response data – measured with millisecond accuracy – whose mining can produce valuable, actionable intelligence through data sifting algorithms. Such sifting modules assess various learning techniques so as to orient students most efficiently. Over time, such student data also charts valuable long-term progress. There’s a quasi-infinite number of axes/dissectors along which to measure student learning susceptibility:
- time of day (morning/afternoon)
- sensory cues (visual/audio/contextual)
- positive/negative social reinforcement
- group competition/team cooperation
- public/private scoring
- humor cues
- self-confidence reinforcement
- neuro-linguistic programming (NLP) cues
- whichever sieve an educator/linguist may want to use
Processing so much orthogonal (n-dimensional) data to produce one aggregate human-readable report calls for complex algorithms often categorized as Artificial Intelligence. However, Linguamix’s complexity isn’t quite as bewildering as it seems, and is well within reach of a traditional (relatively low-key) development department by using 3rd party AI libraries.