# Changelog of X Tweet Classifier with AI Analysis | $0.0003/Tweet (`xquik/x-twitter-tweet-classifier`) Actor

- **URL**: https://apify.com/xquik/x-twitter-tweet-classifier/changelog.md
- **Full Actor documentation**: https://apify.com/xquik/x-twitter-tweet-classifier.md

## Changelog

### 0.1.0, unreleased

- Analyze 16 posts at a time by default, up from 4. A run of 50 posts takes
  about half the time. `analysis.concurrency` still accepts 1 through 16.
- Add the `texts` input. The Actor analyzes your own texts & fetches nothing
  from X for them. Each analyzed text costs the same as an analyzed tweet.
- Run every source of a mixed input: lists, tweet IDs & searches share
  `maxItems`. Earlier the first source ran alone.
- Accept 16 more field names from other tweet Actors, such as `sort`,
  `tweetLanguage`, `author`, `start` & `end`.
- Every row lists `cashtags`; change tracking holds decisions through near-tie
  jitter (comparison rule `decision:3`).
- Summary gains per-target answer splits, per-cashtag signal scores, linked
  source domain counts & monitor change counts; every row lists `sourceDomains`.
- Compare with an earlier run through `monitor.baselineDatasetId`: every row
  reports `first_run`, `new_to_baseline`, `unchanged` or `changed` with the
  decisions that moved.
- Run summary in the `analysis-summary` key-value record & the run report:
  per-question splits, engagement-weighted shares, top tweets per category,
  target mentions & cashtag counts.
- Flat `answers` map on every row & a `Flat answers` dataset view for
  spreadsheet exports.
- Add custom questions, typed answers & original tweet retention.
- Reuse filtered extraction & durable successful-analysis billing.
- Add input, result & diagnostic schemas.
- Upload analyzed rows without platform charging attempts.
- Restructure the README to Apify's recommended section order.

Live qualification & publication remain pending.