New post: Tagging my blog with BERTopic and LLMs.
I suspect as token costs increase, we'll see more blended traditional ML/LLM systems. And, in general, they work really well!
vickiboykis.com/2026/05/18/t...
I suspect as token costs increase, we'll see more blended traditional ML/LLM systems. And, in general, they work really well!
vickiboykis.com/2026/05/18/t...
Tagging my blog posts with BERTopic and LLMs
LLMs mean you still need a human in the loop, but in a different part
vickiboykis.com
May 19, 2026 at 10:51 AM
New post: Tagging my blog with BERTopic and LLMs.
I suspect as token costs increase, we'll see more blended traditional ML/LLM systems. And, in general, they work really well!
vickiboykis.com/2026/05/18/t...
I suspect as token costs increase, we'll see more blended traditional ML/LLM systems. And, in general, they work really well!
vickiboykis.com/2026/05/18/t...
A final desperate plea. Who's using BERTopic in sociology? Showcase your work!
I'm looking for examples of papers published in sociology (or a *closely* related discipline) that use BERTopic. Anything?
August 6, 2025 at 5:52 PM
A final desperate plea. Who's using BERTopic in sociology? Showcase your work!
I'm looking for examples of papers published in sociology (or a *closely* related discipline) that use BERTopic. Anything?
August 6, 2025 at 4:19 AM
I'm looking for examples of papers published in sociology (or a *closely* related discipline) that use BERTopic. Anything?
Use LDA. But if you want to use BERTopic, this is a very thorough and clear guide!
What are the main issues discussed in a set of documents?
We’ve just released a step-by-step BERTopic tutorial.
We also launch a new page, gathering various NLP tutorials for social scientists.
👉 www.css.cnrs.fr/tutorials-an...
We’ve just released a step-by-step BERTopic tutorial.
We also launch a new page, gathering various NLP tutorials for social scientists.
👉 www.css.cnrs.fr/tutorials-an...
Tutorials and Resources – CSS @ IP-Paris
Site web de l'axe sciences sociales computationnelles du CREST-CNRS. Cours et tutoriels pour l'analyse des données numériques en sciences sociales.
www.css.cnrs.fr
January 28, 2026 at 3:28 PM
Use LDA. But if you want to use BERTopic, this is a very thorough and clear guide!
Here's what they don't tell you about topic modeling: preprocessing determines everything. Corpus homogeneity, document length, and context windows matter more than algorithm choice. BERTopic won't fix bad inputs. No model will.
The General Inquirer in the time of LLMs: a BERTopic tutorial – CSS@IPP — Tutorials and resources
A. Morin
css-polytechnique.github.io
February 6, 2026 at 3:47 PM
Here's what they don't tell you about topic modeling: preprocessing determines everything. Corpus homogeneity, document length, and context windows matter more than algorithm choice. BERTopic won't fix bad inputs. No model will.
New article!
The aesthetics of climate misinformation: computational multimodal framing analysis with BERTopic and CLIP by Anton Törnberg & Petter Törnberg / @pettertornberg.com
doi.org/10.1080/0964...
The aesthetics of climate misinformation: computational multimodal framing analysis with BERTopic and CLIP by Anton Törnberg & Petter Törnberg / @pettertornberg.com
doi.org/10.1080/0964...
September 17, 2025 at 6:12 AM
New article!
The aesthetics of climate misinformation: computational multimodal framing analysis with BERTopic and CLIP by Anton Törnberg & Petter Törnberg / @pettertornberg.com
doi.org/10.1080/0964...
The aesthetics of climate misinformation: computational multimodal framing analysis with BERTopic and CLIP by Anton Törnberg & Petter Törnberg / @pettertornberg.com
doi.org/10.1080/0964...
BERTopic users: how do you retrieve the documents most associated with a given topic? I can see some possible options from the documentation, but I'm most interested in standard practice
(NB: please don't take this question as a tacit endorsement of BERTopic, I'm just trying to evaluate it fairly)
(NB: please don't take this question as a tacit endorsement of BERTopic, I'm just trying to evaluate it fairly)
December 4, 2024 at 12:44 PM
BERTopic users: how do you retrieve the documents most associated with a given topic? I can see some possible options from the documentation, but I'm most interested in standard practice
(NB: please don't take this question as a tacit endorsement of BERTopic, I'm just trying to evaluate it fairly)
(NB: please don't take this question as a tacit endorsement of BERTopic, I'm just trying to evaluate it fairly)
I'm reading a paper that compares BERTopic and LDA for tweets and includes:
1. a 2020 citation for LDA, not a single mention of Blei 😐
2. de-duplication BEFORE removing usernames 😟
3. stemming, lemmatizing, etc. ONLY for LDA 😨
4. gensim 😱
It has 1k citations! 🤯
1. a 2020 citation for LDA, not a single mention of Blei 😐
2. de-duplication BEFORE removing usernames 😟
3. stemming, lemmatizing, etc. ONLY for LDA 😨
4. gensim 😱
It has 1k citations! 🤯
December 8, 2025 at 9:41 PM
I'm reading a paper that compares BERTopic and LDA for tweets and includes:
1. a 2020 citation for LDA, not a single mention of Blei 😐
2. de-duplication BEFORE removing usernames 😟
3. stemming, lemmatizing, etc. ONLY for LDA 😨
4. gensim 😱
It has 1k citations! 🤯
1. a 2020 citation for LDA, not a single mention of Blei 😐
2. de-duplication BEFORE removing usernames 😟
3. stemming, lemmatizing, etc. ONLY for LDA 😨
4. gensim 😱
It has 1k citations! 🤯
LLM, BERTopic, etc., are based on existing math and science. There was no new “theory” generated for AI. In fact, the absolute train wreck of its roll out was due to a complete lack of thought and investigation.
August 20, 2026 at 8:01 PM
LLM, BERTopic, etc., are based on existing math and science. There was no new “theory” generated for AI. In fact, the absolute train wreck of its roll out was due to a complete lack of thought and investigation.
Had a great time presenting my poster exploring people's thoughts & feelings about death w/ #BERTopic this evening at the Society for Research in Psychopathology Annual Meeting! Thanks to everyone who stopped by to chat– it was wonderful learning more about others' work and nerding out! 💀🪦
#SRP2025
#SRP2025
September 26, 2025 at 5:56 AM
@felwert LDA seems to take language at face value, whereas BERTopic seems better for handling hierarchically-organized and context-laden semantic structures that resemble what one might experience when doing qualitative coding. BERTopic is also better for shorter text, snippets, etc, which is […]
Original post on archaeo.social
archaeo.social
September 22, 2026 at 4:04 PM
@felwert LDA seems to take language at face value, whereas BERTopic seems better for handling hierarchically-organized and context-laden semantic structures that resemble what one might experience when doing qualitative coding. BERTopic is also better for shorter text, snippets, etc, which is […]
🐧 **BERTopic – topic modeling**
BERTopic is a Python package for topic modeling that uses transformer-based embeddings and class-based TF-IDF. The post BERTopic – topic modeling appeared first on LinuxLinks.
📰 Source: LinuxLinks
🔗 Link: https://www.linuxlinks.com/bertopic-topic-modeling/ […]
BERTopic is a Python package for topic modeling that uses transformer-based embeddings and class-based TF-IDF. The post BERTopic – topic modeling appeared first on LinuxLinks.
📰 Source: LinuxLinks
🔗 Link: https://www.linuxlinks.com/bertopic-topic-modeling/ […]
Original post on igeek.gamer-geek-news.com
igeek.gamer-geek-news.com
June 8, 2026 at 10:18 PM
🐧 **BERTopic – topic modeling**
BERTopic is a Python package for topic modeling that uses transformer-based embeddings and class-based TF-IDF. The post BERTopic – topic modeling appeared first on LinuxLinks.
📰 Source: LinuxLinks
🔗 Link: https://www.linuxlinks.com/bertopic-topic-modeling/ […]
BERTopic is a Python package for topic modeling that uses transformer-based embeddings and class-based TF-IDF. The post BERTopic – topic modeling appeared first on LinuxLinks.
📰 Source: LinuxLinks
🔗 Link: https://www.linuxlinks.com/bertopic-topic-modeling/ […]
I started working on this with BERTopic but also have something else I’d like to get done first https://maartengr.github.io/BERTopic/getting_started/online/online.html
Online Topic Modeling - BERTopic
Leveraging BERT and a class-based TF-IDF to create easily interpretable topics.
maartengr.github.io
July 27, 2023 at 1:49 PM
I started working on this with BERTopic but also have something else I’d like to get done first https://maartengr.github.io/BERTopic/getting_started/online/online.html
What are the main issues discussed in a set of documents?
We’ve just released a step-by-step BERTopic tutorial.
We also launch a new page, gathering various NLP tutorials for social scientists.
👉 www.css.cnrs.fr/tutorials-an...
We’ve just released a step-by-step BERTopic tutorial.
We also launch a new page, gathering various NLP tutorials for social scientists.
👉 www.css.cnrs.fr/tutorials-an...
Tutorials and Resources – CSS @ IP-Paris
Site web de l'axe sciences sociales computationnelles du CREST-CNRS. Cours et tutoriels pour l'analyse des données numériques en sciences sociales.
www.css.cnrs.fr
January 27, 2026 at 3:16 PM
What are the main issues discussed in a set of documents?
We’ve just released a step-by-step BERTopic tutorial.
We also launch a new page, gathering various NLP tutorials for social scientists.
👉 www.css.cnrs.fr/tutorials-an...
We’ve just released a step-by-step BERTopic tutorial.
We also launch a new page, gathering various NLP tutorials for social scientists.
👉 www.css.cnrs.fr/tutorials-an...
The BERTopic tutorial focuses on its underlying philosophy, as well as on the merits and limitations of this widely used tool.
Carefully written by @Axel Morin (CSS@IP-Paris) , it explain how to apply BERTopic in a social science project.
👉 css-polytechnique.github.io/css-ipp-mate...
Carefully written by @Axel Morin (CSS@IP-Paris) , it explain how to apply BERTopic in a social science project.
👉 css-polytechnique.github.io/css-ipp-mate...
The General Inquirer in the time of LLMs: a BERTopic tutorial – CSS@IPP — Tutorials and resources
css-polytechnique.github.io
January 27, 2026 at 3:16 PM
The BERTopic tutorial focuses on its underlying philosophy, as well as on the merits and limitations of this widely used tool.
Carefully written by @Axel Morin (CSS@IP-Paris) , it explain how to apply BERTopic in a social science project.
👉 css-polytechnique.github.io/css-ipp-mate...
Carefully written by @Axel Morin (CSS@IP-Paris) , it explain how to apply BERTopic in a social science project.
👉 css-polytechnique.github.io/css-ipp-mate...
The python package is well documented and feels modern, and most of the obvious python LDAs use stochastic variational. Both BERTopic and SV LDA are good enough that they seem to work, but not really that good. The weakness in BERTopic is that embedding data doesn't really work with HDBSCAN.
September 22, 2026 at 4:57 PM
The python package is well documented and feels modern, and most of the obvious python LDAs use stochastic variational. Both BERTopic and SV LDA are good enough that they seem to work, but not really that good. The weakness in BERTopic is that embedding data doesn't really work with HDBSCAN.
Digging a little more into the evaluation. They compare their results to BERTopic; an author annotated the BERTopic topics with labels and then measured overlap in concepts between BERTopic and LlooM, and then compared these results to datasets with predetermined categories.
January 17, 2025 at 1:42 PM
Digging a little more into the evaluation. They compare their results to BERTopic; an author annotated the BERTopic topics with labels and then measured overlap in concepts between BERTopic and LlooM, and then compared these results to datasets with predetermined categories.
Have you seen this:
maartengr.github.io/BERTopic/ind...
maartengr.github.io/BERTopic/ind...
BERTopic
Leveraging BERT and a class-based TF-IDF to create easily interpretable topics.
maartengr.github.io
April 9, 2025 at 8:04 PM
Have you seen this:
maartengr.github.io/BERTopic/ind...
maartengr.github.io/BERTopic/ind...
Incoming feature for #ActiveTigger : compute easily exploratory #bertopic on your data to identify topics before moving on to annotation task
August 21, 2025 at 1:45 PM
Incoming feature for #ActiveTigger : compute easily exploratory #bertopic on your data to identify topics before moving on to annotation task
New paper 🚨 “Vicarious denial: war crimes & online deliberation in Serbia” 🇷🇸 with @denisakost.bsky.social
We scrape 4 news sites + reader comments and blend text-as-data (keywords; neg. binomial/logistic; BERTopic/SBERT) with critical discourse analysis to track on-topic debate & denial.
We scrape 4 news sites + reader comments and blend text-as-data (keywords; neg. binomial/logistic; BERTopic/SBERT) with critical discourse analysis to track on-topic debate & denial.
October 9, 2025 at 1:29 AM
New paper 🚨 “Vicarious denial: war crimes & online deliberation in Serbia” 🇷🇸 with @denisakost.bsky.social
We scrape 4 news sites + reader comments and blend text-as-data (keywords; neg. binomial/logistic; BERTopic/SBERT) with critical discourse analysis to track on-topic debate & denial.
We scrape 4 news sites + reader comments and blend text-as-data (keywords; neg. binomial/logistic; BERTopic/SBERT) with critical discourse analysis to track on-topic debate & denial.
Announcing BERTopic v0.17 🥳
This is a feature-packed update that includes the amazing Model2Vec, more interactive DataMapPlot functionalities, a method for lightweight installation, and much more!
This is a feature-packed update that includes the amazing Model2Vec, more interactive DataMapPlot functionalities, a method for lightweight installation, and much more!
March 19, 2025 at 5:09 PM
Announcing BERTopic v0.17 🥳
This is a feature-packed update that includes the amazing Model2Vec, more interactive DataMapPlot functionalities, a method for lightweight installation, and much more!
This is a feature-packed update that includes the amazing Model2Vec, more interactive DataMapPlot functionalities, a method for lightweight installation, and much more!
👀
I've had mixed experiences with BERTopic but I'm very happy to see this tutorial
And more to come, it seems?
I've had mixed experiences with BERTopic but I'm very happy to see this tutorial
And more to come, it seems?
What are the main issues discussed in a set of documents?
We’ve just released a step-by-step BERTopic tutorial.
We also launch a new page, gathering various NLP tutorials for social scientists.
👉 www.css.cnrs.fr/tutorials-an...
We’ve just released a step-by-step BERTopic tutorial.
We also launch a new page, gathering various NLP tutorials for social scientists.
👉 www.css.cnrs.fr/tutorials-an...
Tutorials and Resources – CSS @ IP-Paris
Site web de l'axe sciences sociales computationnelles du CREST-CNRS. Cours et tutoriels pour l'analyse des données numériques en sciences sociales.
www.css.cnrs.fr
January 28, 2026 at 5:59 AM
👀
I've had mixed experiences with BERTopic but I'm very happy to see this tutorial
And more to come, it seems?
I've had mixed experiences with BERTopic but I'm very happy to see this tutorial
And more to come, it seems?
Qualitatively, I found that the BERTopic groupings were still rather large, so I anticipate the GPT labels would still be quite generic (as opposed to specific/targeted concepts).
January 17, 2025 at 5:18 PM
Qualitatively, I found that the BERTopic groupings were still rather large, so I anticipate the GPT labels would still be quite generic (as opposed to specific/targeted concepts).
📢TextAnalysisR is now on CRAN: an R package + Shiny app for text mining: topic models (STM/BERTopic), sentiment, and semantic networks. #rstats #NLP #LLM
install.packages("TextAnalysisR")
App: textanalysisr.org
Doc: mshin77.github.io/TextAnalysisR/
install.packages("TextAnalysisR")
App: textanalysisr.org
Doc: mshin77.github.io/TextAnalysisR/
TextAnalysisRTextAnalysisR
TextAnalysisR: A text mining workflow tool
textanalysisr.org
July 30, 2026 at 7:13 PM
📢TextAnalysisR is now on CRAN: an R package + Shiny app for text mining: topic models (STM/BERTopic), sentiment, and semantic networks. #rstats #NLP #LLM
install.packages("TextAnalysisR")
App: textanalysisr.org
Doc: mshin77.github.io/TextAnalysisR/
install.packages("TextAnalysisR")
App: textanalysisr.org
Doc: mshin77.github.io/TextAnalysisR/