I gauged Twitter sentiment evolution towards some key DeFi protocols

Twitter sentiment evolution towards FEI (10k tweet over the period Jan '21 - Sep '21)

Twitter sentiment evolution towards Uniswap (310k tweets over the period Jan '21 - Sep '21)

Twitter sentiment evolution towards Compound proto (128k tweets over the period Feb '20 - Oct '21)


Twitter sentiment evolution towards AAVE proto (256k tweets over the period Nov '19 - Oct '21)

As you can see from the intensification of fluctuations real interest skyrockets witht the start of DeFi summer (239k out of 256k tweets in the period Jun '20 - Oct '21). If you zoom in, you see details better.

An autoencoding BERT derivative language model trained on the corpus of tweets, then fine-tuned on a different corpus of tweets with sentiment labeled by human annotators, then Twitter feed scrapped with inclusion/exclusion @ # $ and some others for a particular protocol. Then run scrapped Twitter feed through language model, then for each data point in the time series calculate rolling mean with a heuristic window (a sweet spot: less ā€“ too much noise, more ā€“ too little details).

Iā€™m working on the tool for protocol simulation and exploration in a coherent unified way, community model being part of it. It could then be used to run stress tests, assess protocol risks, classify protocols and tokens, detect user behaviour patterns, make forecasts about certain protocol KPIs like TVL and in many other ways as a decision support tool for more insightful, informed decision making. Will publish code, comments and roadmap.

More to come: learn.klimchitsky.com