Play Analytics


Analyzing detailed data from SpeechBlocks to understand how kids engage with constructionist literacy learning technologies, with the goal of empowering caregivers (e.g. parents, older siblings, tutors) with these insights.

Play Trees

Data-driven analysis of play using SpeechBlocks

The rich, fine-grained data gathered from SpeechBlocks opens up unique opportunities to go beyond test results and look closely, progressively and longitudinally at the child’s learning process itself  and use the lens of data to study what playful learning looks like.

To reveal the stories hidden in the data , we processed the log files into a semantic/symbolic data structure called Play Trees.  Play Trees abstract the actions of merge, split, and speak and are used to visualize the process of word construction. 

The following video demonstrates the concept of  Play Trees  by visualizing a  sample story from the data.

We use the raw data and Play Trees to understand both what children are building and how they’re building it. We first want to understand whether the words created are sensible by looking at the directionality of the text, misspellings, the context in which they were created, the pronounceability, and instances of word or letter repetition, etc.

More info on this project can be found at:                                      

Family Learning Coaching Tool

Translating Play Tree data into meaningful information for families.

To empower a literacy learning coach (e.g. community volunteers, grandparents, family friends), we have created a prototype of a Family Learning Coaching Tool that can be used to quickly create highlights for parents .

These highlights discuss developmental milestones such as a new word that the child created for the first time, specific sounds that they explored that day, invented spellings that they created for a word, etc. We use insights from the Play Tress  to illustrate these milestones with specific examples from the child's play on SpeechBlocks.

More info on this project can be found at: