Jev X Sentiment Analysis
Crypto terminal that condenses up to 1,000 posts plus market data into a Jev buy, sell, hold or take-profit card; no trading.
Overview
Jev X Sentiment Analysis is an on-demand crypto market intelligence terminal. You search a ticker such as BTC, SOL or ETH and choose how many posts from X to analyse, from 50 to 1,000. It pulls live price, volume, RSI, funding rate and open interest through CCXT and posts through TwitterAPI.io, then runs a three-stage pipeline instead of dumping every post into a model.
Stage one computes engagement velocity, author diversity (to detect bot farms) and keyword sentiment polarity, and extracts the 25 most engaged and 25 most recent posts. Stage two stores posts in SQLite and stops paginating as soon as it hits a known post, filling the sample from the database to save API credits. Stage three asks Jev four typed questions on the combined state: a trade action Choice (strong buy to strong sell, including take profit), a sentiment Score from extreme panic to euphoria, a short-squeeze Noul and a catalyst significance Score. The result is a decision card with confidence, entry range, stop loss and targets; it never executes trades. The README estimates under a cent for 50 posts. It is not financial advice and had no licence file at listing time.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | What trade action does the evidence support? | Strong Buy · Buy · Hold · Take Profit · Sell · Strong Sell |
| Score | Where is sentiment on the spectrum from extreme panic to euphoria? | — |
| Yes / no | Do negative funding and panic indicate a likely short squeeze? | — |
| Score | How significant is the catalyst? | None · Minor · Moderate · Major |
How it works
- Fetch market data and posts
- Statistical pre-processing and stratified sampling
- SQLite deduplication with early stopping
- Jev answers four questions; show a decision card for manual execution
Strengths
- Avoids sending hundreds of raw posts to a model
- Low per-search cost per the README
- Never executes trades
Caveats
- Not financial advice
- No licence file at listing time
- Depends on paid third-party post API
At a glance
- Type
- Project
- Status
- prototype
- Language
- Python
- Runtime
- Web terminal
- Has code
- yes
Use cases and integrations
How curated lists describe it
Crypto decision support: ingests 50-1,000 tweets per request through statistical pre-processing and SQLite deduplication, then has Jev turn the surviving evidence into a decision card with entry ranges, stop losses, and targets, without executing trades.
yibie/awesome-jevCrypto terminal that reads up to 1,000 posts about a ticker alongside market and funding data and turns them into a buy, sell, hold, or take-profit call. No license file at the time of writing. Not financial advice.
MrJev/awesome-jev
Frequently asked questions
Does it place trades?
No, it produces a decision card for you to act on manually.
What does Jev decide?
Trade action, sentiment level, squeeze risk and catalyst significance.
How does it keep costs down?
Statistical pre-processing, stratified sampling and SQLite deduplication before calling Jev.
Related projects
Research wiring LAYA/Jev typed decisions into a quant stack with Claude fallback: good news reading, no market-beating edge.
ProjectresearchPythonStudy of whether Jev's reading of financial news predicts stock returns: strong same-day signal, no tradeable alpha.
BenchmarkresearchGoValence: macro news sentiment engine scoring global headlines' market impact with a contrastive System-One model on serverless GPU.
ProjectprototypePythonLocal China A-share technical analysis workbench where Jev assesses eight indicator dimensions and returns Buy, Hold or Sell with evidence.
ProjectbetaPython, TypeScriptLocal stock decision service that sends market data and news to Jev or a local model and returns a policy-checked buy/sell/hold.
ProjectbetaTypeScriptPyTorch factor-research stack with 213 factors and cost-aware backtests, plus a preview typed portfolio-decision adapter.
ProjectbetaPython