Thread by @CamachoCollados

📢 Today we officially launch TweetNLP, an all-round NLP platform for social media. From sentiment analysis to emoji prediction and more 🔥🔥

✔️ TweetNLP includes a Python API, a demo and tutorials. Useful for developers and researchers alike. Want to know more? 🧵

Everything you need is at ➡️tweetnlp.org⬅️

TweetNLP is powered by relatively light-weight transformer-based language models, which can be run on most computers or free cloud services.

So, what’s in it for you? 👇

1⃣ <Python API>

Step 1: pip install tweetnlp

Step 2: import tweetnlp

Step 3: model = tweetnlp.load('sentiment')

Step 4: model.sentiment("We love NLP!🥰")

github.com/cardiffnlp/twe…

2⃣<Interactive Demo>

Test our models without having to write a line of code (tweet classification, tweet similarity, named entity recognition, masked language modelling, etc.)

Or you can even type a hashtag or keyword and retrieve an aggregated analysis of what’s going on in Twitter! #NLProc

3⃣ <Tutorials>

Get started with TweetNLP using our user-friendly Google Colab notebooks, including started code and plenty of examples. Familiarise yourself with language models and simple social media tasks.

For those of you academics like myself that would like to see everything summarised in a paper, we also got you covered! 😄 

”TweetNLP: Cutting-Edge Natural Language Processing for Social Media”

Paper link 👉 arxiv.org/abs/2206.14774

Thank you to everyone involved in this project!🤗

@kiamehrrezaee @asahiushio @danielbloureiro @dimos_antypas @Jojo62219574 @espinosaanke @hardy_qr @genimarca @tom_gxt @lnevespapers @fvancesco

And of course, TweetNLP has an associated Twitter account 😆 

👉Follow @tweet_nlp!

/END