Tweets Analysis - Keyword: @spacy_io
Overview
Total number of tweets analysed
63
Earliest tweet was on
2023-02-11
Latest tweet was on
2023-02-20
Tweets covering
8 days
Average age of authors' accounts
9 years
Summarization
The latest version of BERTopic (v0.14) offers support for fine-tuning of topic keywords and labels using tools such as OpenAI, Huggingface, CohereAI, Spacy_IO and LangChainAI for various tasks such as part-of-speech tagging, text generation and zero-shot classification. Various activities related to the use of NLP and data science are being done such as the development of a NLP pipeline for COVID and corpus of 430,000 words through tokenization, lemma analysis and entity detection. Furthermore, feasibility of using AI tools for commercial use with the current influx of new tools is also being discussed.
Topic Modeling
- NLP tools such as OpenAI, Huggingface, CohereAI, Spacy_io, and LangChainAI
- Using models for part-of-speech tagging, text generation, zero shot classification, etc.
- Demo from the data science/NLP team of @APHP
- Tokenizing, Lemma-analysis, Entity recognition
- Entity Linking, Semantic Segmentation, GPT3, and Corpus of Spanish Language
Emotional Analysis
The tweets in this sample express a wide range of emotions, from excitement and enthusiasm about the release of the BERTopic v0.14, to admiration for the powerful tools offered by OpenAI, Huggingface, CohereAI, Spacy_io, and LangChainAI, to anticipation for a fireside chat and eagerness to try out the new version. There is also a sense of pride in the work of the APHP data science/NLP team and their accomplishments. Finally, the tweets show a sense of awe at the potential of AI tools, as well as a sense of camaraderie and support for the efforts of the developers.
Trend Analysis
- Usage of NLP tools (OpenAI, Huggingface, CohereAI, Spacy_io, LangChainAI)
- Fine-tune topic keywords and labels
- Usage of NLP tools in production, challenges and use cases
- Automatically transcription of videos
- Using AI tools to turn a profit
Types of Tweets
Number of Retweets
17
Percentage of total tweets
26%
Number of Original tweets
2
Percentage of total tweets
3%
Number of tweets that contain Mentions
63
Percentage of total tweets
100%
Number of tweets that were Replies
50
Percentage of total tweets
79%
Number of tweets that were Quotes
3
Percentage of total tweets
4%
Number of tweets that contain Hashtags
6
Percentage of total tweets
9%
Top 5 devices used to tweet
| Source | Count |
|---|---|
| Twitter Web App | 24 |
| Twitter for Android | 13 |
| Twitter for iPhone | 12 |
| Twitter for iPad | 8 |
| mem.ai | 6 |
What devices were used to tweet
Top 10 accounts with highest followers count
| Username | Name | Bio | Followers count |
|---|---|---|---|
| DataChaz | DataChazGPT 🤯 (not a bot) | ∙ Developer 🥑 at 🎈@Streamlit ❄️@snowflakedb∙ Obsessed with: #ChatGPT #SEO #DataScience∙ 🧙♂️ Open Sourcerer∙ @SEOPythonistas maintainer 🐍🔥 🇫🇷 🇬🇧 | 66,434 |
| memdotai | Mem | Your self-organizing workspace.Get Mem It for Twitter: https://t.co/PXu0Fqq8k1…Website: https://t.co/XSDVK00mbv Community: https://t.co/arZa1ml8IS | 40,155 |
| spacy_io | spaCy | Open-source library for industrial-strength Natural Language Processing in Python. Developed by @explosion_ai 💥 📖 https://t.co/YkVR838V7S 📘 https://t.co/6kqoeWgvd2 📺 https://t.co/46ioYHURlW | 25,304 |
| GaelVaroquaux | Gael Varoquaux GaelVaroquaux@mastodon.social | Research & code: Research director @inria►Data, Health, & Computer science►Python coder, (co)founder of @scikit_learn & joblib►Art on @artgael►Physics PhD | 21,357 |
| hugobowne | Hugo Bowne-Anderson is podcasting again | data scientist, writer, educator, anecdotalist, head of developer relations @outerboundshq, host of @vanishingdata podcast https://t.co/XadXHlEsAx | 13,470 |
| NirantK | Nirant | Wrote a NLP book for Python Devs: https://t.co/mgti5Vulhv | @stanford recommends Awesome NLP which I maintain! | 7,965 |
| jessyseonoob | ⚡Jessy SEO Expert #Jasper #GPT3 #redaction 🌟 🦊 | 🦊#CopyWritingAI 🎓 Consultant #SEO Marseille 👽 MEDIACREA #ecommerce🛒 wordpress 🚀 #seo 🤖#JasperAi certifié activateur #francenum #ChatGPT Laurent JEAN | 6,707 |
| pixelbeat | Davo Galavotti | Working on Serverless Observability. Exploring AI & Applied ML for creative tools. Blender poser. | 5,302 |
| zehavoc | Djamé.. | Associate professor in NLP, engaged citizen. Tweeting about work, life and stuffs that I care about. All my tweets can be used freely. @zehavoc@mastodon.social | 5,021 |
| the_claus | Claus Hesseling | Data Journalist, Stories and Code @NDR Data - Trainer @interlinkaca @ARDZDF_Akademie @djsde - Husband, Father and Time Traveller. PGP 7913C96B | 3,600 |
Top 10 accounts with highest friends count
| Username | Name | Bio | Followers count |
|---|---|---|---|
| DataChaz | DataChazGPT 🤯 (not a bot) | ∙ Developer 🥑 at 🎈@Streamlit ❄️@snowflakedb∙ Obsessed with: #ChatGPT #SEO #DataScience∙ 🧙♂️ Open Sourcerer∙ @SEOPythonistas maintainer 🐍🔥 🇫🇷 🇬🇧 | 28,747 |
| ayirpelle | priya joseph | geek, entrepreneur, 'I strictly color outside the lines!', opinions r my own indeed. @ayirpelle , universal handle at this time | 5,002 |
| davidherbertlee | David Lee | Cyber Security postgraduate research student. neurodiverse nerd. | 4,480 |
| DrJoshZhang | Josh Zhang | Computational sociologist @ SBU. Views mine. Doing big data and CSS. Love freedom. Follow me @yz@sciences.social Photo: Rongbu Temple, the highest temple | 3,764 |
| the_claus | Claus Hesseling | Data Journalist, Stories and Code @NDR Data - Trainer @interlinkaca @ARDZDF_Akademie @djsde - Husband, Father and Time Traveller. PGP 7913C96B | 3,470 |
| hugobowne | Hugo Bowne-Anderson is podcasting again | data scientist, writer, educator, anecdotalist, head of developer relations @outerboundshq, host of @vanishingdata podcast https://t.co/XadXHlEsAx | 3,439 |
| zehavoc | Djamé.. | Associate professor in NLP, engaged citizen. Tweeting about work, life and stuffs that I care about. All my tweets can be used freely. @zehavoc@mastodon.social | 2,788 |
| mehmetgoekce | Mehmet Gökçe | Software & Data Engineer, Consultant | CEO & FOUNDER - MEMOTEC @MemoTecAgency | | 2,039 |
| jessyseonoob | ⚡Jessy SEO Expert #Jasper #GPT3 #redaction 🌟 🦊 | 🦊#CopyWritingAI 🎓 Consultant #SEO Marseille 👽 MEDIACREA #ecommerce🛒 wordpress 🚀 #seo 🤖#JasperAi certifié activateur #francenum #ChatGPT Laurent JEAN | 1,761 |
| _koichiro | Koichiro TAJIMA | #innovation, #Comportements #Digitaux, #SocialMedia, #politique, art contemporain, Jazz, Guitar｜#rstats #machinelearning｜日記と拾い物のメモ | 1,653 |
Most active users
| Username | Bio | Number of tweets |
|---|---|---|
| zehavoc | Associate professor in NLP, engaged citizen. Tweeting about work, life and stuffs that I care about. All my tweets can be used freely. @zehavoc@mastodon.social | 7 |
| talbaumel | אני טל | 7 |
| memdotai | Your self-organizing workspace.Get Mem It for Twitter: https://t.co/PXu0Fqq8k1…Website: https://t.co/XSDVK00mbv Community: https://t.co/arZa1ml8IS | 6 |
| cohenrap | Helping AI understand people, so AI could help people understand people@cohenrap@sigmoid.social | 5 |
| MaartenGr | Data Scientist | Psychologist | Open Source Developer (BERTopic, PolyFuzz, KeyBERT). @MaartenGr@fosstodon.org | 3 |
| eric360io | - | 3 |
| EmilyMcGrath01 | PhD in progress | Political Economy of Li Extraction for Decarbonisation Technologies | Decolonising the Energy Transition | Data Scientist | she/her | 2 |
| willman20 | #CTO @Editialis passionné par : #SEO, #WebAnalytics, #ML, #R, #Pyhton, #DataScience, dév. Web, architecture de l'information. | 1 |
| ur_mr_Legend | Data Scientist, NLP, Politics, Opinions, Roboticist, Drone Researcher, UPSC Survivor, Entrepreneur, Electrical Engineer, IIT Bombay. | 1 |
| the_claus | Data Journalist, Stories and Code @NDR Data - Trainer @interlinkaca @ARDZDF_Akademie @djsde - Husband, Father and Time Traveller. PGP 7913C96B | 1 |
Tweets per day
Top 10 tweets with highest Retweet count
| ID | Text | Retweet count |
|---|---|---|
| 1625514341331001351 | The v0.14 release of BERTopic is here 🥳 Fine-tune your topic keywords and labels with models from @OpenAI, @huggingface, @CohereAI, @spacy_io, and @LangChainAI. Use models for part-of-speech tagging, text generation, zero-shot classification, and more! An overview thread👇🧵 https://t.co/Bjxr7CnMHE | 124 |
| 1625843012184973312 | Wow! #BERTopic just got an incredible upgrade! 🤯👇Pick your #NLP tool → @OpenAI, @Huggingface, @CohereAI, @Spacy_io, all of which can now be combined thanks to the mighty @LangChainAI! 🔥 https://t.co/KksVubEFEQ | 28 |
| 1625068750277074944 | Next week I'll be speaking with @_inesmontani about NLP in production, trends, and patterns, challenges, use cases (yes, LLMs also 😜), and @spacy_io. Sign up for our @OuterboundsHQ fireside chat below 👇 https://t.co/2UivFGIUGc | 13 |
| 1626541696329695233 | Cool demo from the data science/NLP team of @APHP (hospital system of Paris, University and all) showing a minimal NLP pipeline, here covid oriented, they built. They released a lot of stuff (@spacy_io based) on their github https://t.co/NwCWY7HYVj | 1 |
| 1627682549395820545 | @tom_gxt We do not have non-trivial entity linking in dirty-cat.From actual text, I believe that @spacy_io does entity resolution and is easy to use.If you are starting from tables (as in the example), it's a slightly different problem. Maybe you can build a hack on top of @spacy_io | 0 |
| 1625910300846305297 | "Check out the new #LangChainAI platform, which allows you to combine the best NLP tools from @OpenAI, @Huggingface, @CohereAI, and @Spacy_io to create powerful solutions! 🔥" https://t.co/eRxQZFcZeJ | 0 |
| 1626019310916505600 | @MaartenGr @OpenAI @huggingface @CohereAI @spacy_io @LangChainAI @memdotai mem it | 0 |
| 1625998907523190785 | @DataChaz @OpenAI @huggingface @CohereAI @spacy_io @LangChainAI @SaveToNotion #thread #ai | 0 |
| 1625950911259414565 | @willman20 @MaartenGr @OpenAI @huggingface @CohereAI @spacy_io @LangChainAI ...includes part-of-speech tagging, text generation, zero-shot classification, and more. Users can also chain different models to sequentially fine-tune the topic keywords and labels. Learn more about BERTopic and the new models here." | 0 |
| 1625950908747026457 | @willman20 @MaartenGr @OpenAI @huggingface @CohereAI @spacy_io @LangChainAI Saved! Here's the compiled thread: https://t.co/3A3oswRhZH🪄 AI-generated summary:"BERTopic v0.14 has been released, allowing users to fine-tune their topic keywords and labels with models from OpenAI, HuggingFace, CohereAI, Spacy, and LangChainAI. This... | 0 |
Top 10 tweets with highest Like count
| ID | Text | Like count |
|---|---|---|
| 1625514341331001351 | The v0.14 release of BERTopic is here 🥳 Fine-tune your topic keywords and labels with models from @OpenAI, @huggingface, @CohereAI, @spacy_io, and @LangChainAI. Use models for part-of-speech tagging, text generation, zero-shot classification, and more! An overview thread👇🧵 https://t.co/Bjxr7CnMHE | 797 |
| 1625843012184973312 | Wow! #BERTopic just got an incredible upgrade! 🤯👇Pick your #NLP tool → @OpenAI, @Huggingface, @CohereAI, @Spacy_io, all of which can now be combined thanks to the mighty @LangChainAI! 🔥 https://t.co/KksVubEFEQ | 117 |
| 1625068750277074944 | Next week I'll be speaking with @_inesmontani about NLP in production, trends, and patterns, challenges, use cases (yes, LLMs also 😜), and @spacy_io. Sign up for our @OuterboundsHQ fireside chat below 👇 https://t.co/2UivFGIUGc | 44 |
| 1626541696329695233 | Cool demo from the data science/NLP team of @APHP (hospital system of Paris, University and all) showing a minimal NLP pipeline, here covid oriented, they built. They released a lot of stuff (@spacy_io based) on their github https://t.co/NwCWY7HYVj | 11 |
| 1626615640755777537 | Dazu haben wir die Kanalvideos automatisch verschriftlichen lassen. Herausgekommen ist ein Corpus von rund 430.000 Worten. Mit Hilfe von @spacy_io und NLTK haben wir eine Tokenisierung, Lemma-Analyse und Entitätenerkennung durchgeführt. | 3 |
| 1625551796012781587 | @MaartenGr @OpenAI @huggingface @CohereAI @spacy_io @LangChainAI Awesome work 🥳🚀🚀 OpenAI results are very inspirational | 3 |
| 1625672730032091137 | @MaartenGr @OpenAI @huggingface @CohereAI @spacy_io @LangChainAI 👏👏👏Looking forward to trying out this new version for our topic modeling analyses | 2 |
| 1626547637879992320 | @talbaumel @zehavoc @APHP @spacy_io Charged separately | 2 |
| 1625910007593340928 | @MaartenGr @OpenAI @huggingface @CohereAI @spacy_io @LangChainAI This library going to shine 🔥 keep the hard work going, love it! | 1 |
| 1627213565340880896 | @DataChaz @alton_lex @OpenAI @huggingface @CohereAI @spacy_io @LangChainAI le seigneur des anneaux | 1 |
Top 3 Languages Used In Tweets
Top 10 Hashtags used
| Hashtag | Count |
|---|---|
| #nlp | 3 |
| #thread | 2 |
| #bertopic | 2 |
| #gpt | 1 |
| #ai | 1 |
| #classification | 1 |
| #langchainai | 1 |
Top 10 Hashtags Used In Tweets
Top 10 mentions
| Mention | Count |
|---|---|
| @spacy_io | 64 |
| @openai | 34 |
| @huggingface | 33 |
| @cohereai | 33 |
| @langchainai | 32 |
| @maartengr | 23 |
| @aphp | 20 |
| @zehavoc | 13 |
| @cohenrap | 13 |
| @talbaumel | 12 |
Top 10 mentions
Wordcloud of Tweets
Emojis
Average number of emojis used per tweet
63
Emojis used in tweets
| Emoji | Count | Emoji Text |
|---|---|---|
| 👇 | 7 | backhand_index_pointing_down |
| 🥳 | 4 | partying_face |
| 🔥 | 4 | fire |
| 👏 | 4 | clapping_hands |
| 🧵 | 3 | thread |
| 🪄 | 3 | magic_wand |
| 😌 | 2 | relieved_face |
| 💪 | 2 | flexed_biceps |
| 🤯 | 2 | exploding_head |
| 🚀 | 2 | rocket |
Emojis groups
| Emoji Group | Count |
|---|---|
| People & Body | 13 |
| Smileys & Emotion | 12 |
| Activities | 8 |
| Travel & Places | 6 |
| Food & Drink | 1 |