RRepoGEO

REPOGEO REPORT · LITE

webis-de/small-text

Default branch main · commit 8e97a524 · scanned 6/11/2026, 2:11:49 PM

GitHub: 644 stars · 77 forks

AI VISIBILITY SCORE
40 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface webis-de/small-text, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Reposition README's opening to highlight specialization

    Why:

    CURRENT
    Small-Text provides state-of-the-art **Active Learning** for Text Classification.
    COPY-PASTE FIX
    Small-Text provides state-of-the-art **Active Learning** for Text Classification, specifically designed for modern NLP models like Transformers.
  • mediumcomparison#2
    Add a 'Comparison with Alternatives' section to README

    Why:

    COPY-PASTE FIX
    ## Comparison with Alternatives

While general active learning libraries like `modAL` and `ALiPy` offer broad functionality, `small-text` is uniquely specialized for text classification tasks, providing deep integration and optimized strategies for modern NLP models, including Transformers. Unlike data labeling platforms such as Snorkel or Prodigy, `small-text` focuses on providing a flexible, programmatic library for active learning experimentation and application development.
  • lowreadme#3
    Add a 'Key Features' section to README

    Why:

    COPY-PASTE FIX
    ## Key Features

*   **State-of-the-art Active Learning:** Implementations of various query strategies, initialization strategies, and stopping criteria.
*   **Text Classification Focus:** Optimized for diverse text classification tasks.
*   **Modern NLP Model Support:** Seamless integration with Transformer models (e.g., via Hugging Face Transformers) and other deep learning architectures.
*   **Flexible and Extensible:** Easily mix and match components to build custom active learning pipelines.
*   **Pythonic API:** Designed for ease of use and integration into existing Python workflows.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface webis-de/small-text
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Snorkel
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Snorkel · recommended 1×
  2. Prodigy · recommended 1×
  3. Argilla · recommended 1×
  4. LightTag · recommended 1×
  5. Humanloop · recommended 1×
  • CATEGORY QUERY
    How to efficiently label training data for text classification with limited initial examples?
    you: not recommended
    AI recommended (in order):
    1. Snorkel
    2. Prodigy
    3. Argilla
    4. LightTag
    5. Humanloop
    6. Label Studio

    AI recommended 6 alternatives but never named webis-de/small-text. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Python library for active learning with transformer models in natural language processing?
    you: not recommended
    AI recommended (in order):
    1. modAL
    2. ALiPy
    3. Lightly
    4. libact
    5. Hugging Face Transformers

    AI recommended 5 alternatives but never named webis-de/small-text. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of webis-de/small-text?
    pass
    AI named webis-de/small-text explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts webis-de/small-text in production, what risks or prerequisites should they evaluate first?
    pass
    AI named webis-de/small-text explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo webis-de/small-text solve, and who is the primary audience?
    pass
    AI named webis-de/small-text explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of webis-de/small-text. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/webis-de/small-text.svg)](https://repogeo.com/en/r/webis-de/small-text)
HTML
<a href="https://repogeo.com/en/r/webis-de/small-text"><img src="https://repogeo.com/badge/webis-de/small-text.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

webis-de/small-text — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite