Jev Classifier
Web tool that analyses Telegram channel JSON exports locally for intent, quality, sentiment and speaker tone with Jev.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
Jev Classifier, hosted at jevclassifier.vercel.app, is listed in hellogumbo/awesome-jev as a local analyser for Telegram channel JSON exports. It classifies messages by intent, quality, sentiment and speaker tone.
It is useful for channel owners or researchers wanting a structured view of a channel's content. No README or source was available, so it is unclear how local processing interacts with Jev API calls, which questions are asked, or how results are presented.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | What is the intent of this message?(inferred) | — |
| Choice | What is the sentiment and speaker tone?(inferred) | — |
| Score | How high is the quality of this message?(inferred) | — |
How it works
- Export a Telegram channel as JSON
- Load it into the analyser
- Messages are classified for intent, quality, sentiment and tone
- Review the results
Strengths
- Structured analysis of channel content
Caveats
- No README or source available
- Data handling not documented
At a glance
- Type
- Article
- Status
- prototype
- Runtime
- browser
Use cases and integrations
How curated lists describe it
Local Telegram channel JSON analyzer for intent, quality, sentiment, and speaker tone.
hellogumbo/awesome-jev
Frequently asked questions
What does it analyse?
Telegram channel JSON exports for intent, quality, sentiment and tone.
Is it local?
The list describes it as local, but details are undocumented.
Where can I try it?
At jevclassifier.vercel.app.
Related projects
DeepSeek Harness plugin that classifies each user message's emotion, urgency and department with Jev and injects it as context.
PluginbetaTypeScriptZero-dependency Android app that judges the visible WeChat message's intent, emotion, urgency and reply posture with Jev.
AppbetaJavaAndroid WeChat assistant where Jev judges the chat and scores the relationship, and a chat model drafts three replies.
AppbetaKotlinWeChat plugin that classifies a long-pressed message's intent, emotion, urgency and suggested reply posture with Jev.
PluginbetaJavaLocal chat analyser that labels each WeChat message's emotion and intent with Jev and grades how your replies landed.
ProjectprototypeJavaScriptWeb app that reads a two-person chat and labels each message's emotion, intent and reply quality to estimate interest.
ProjectprototypeTypeScript