Excited to have led a workshop on validating text-as-data and topic models at COMPTEXT24! Ensuring that our analysis meets scientific standards is key & don't forget: validate, validate, validate! #textasdata #topicmodels #COMPTEXT24
@janabernhard.bsky.social discussing Validation in Automated Text Analysis at the COMPTEXT conference now 👀 make sure not to miss Jana’s panel on Saturday morning 📝
May 4, 2024 at 1:41 PM
Excited to have led a workshop on validating text-as-data and topic models at COMPTEXT24! Ensuring that our analysis meets scientific standards is key & don't forget: validate, validate, validate! #textasdata #topicmodels #COMPTEXT24
Qualitative analysis for big data: tidytext and topicmodels: http://osf.io/x2nf5_v1/
February 11, 2025 at 7:35 PM
Qualitative analysis for big data: tidytext and topicmodels: http://osf.io/x2nf5_v1/
On the technical side, combining an LLM API e.g. {claudeR} with some topic modelling e.g. {topicmodels}, to parse topics from generated text would prolly be the way to go. Compare these topics to those in essays - however, longer essays may naturally have more overlap of themes.
Yo!
Academics who set essays,
I have an idea..
I could give Claude and ChatGPT my assessment questions, then design a package which assesses how similar my students’ essays are to those AI generated answers, not just in terms of exact wording but also themes.
Has anyone designed / tried this?
Academics who set essays,
I have an idea..
I could give Claude and ChatGPT my assessment questions, then design a package which assesses how similar my students’ essays are to those AI generated answers, not just in terms of exact wording but also themes.
Has anyone designed / tried this?
November 25, 2024 at 4:00 PM
On the technical side, combining an LLM API e.g. {claudeR} with some topic modelling e.g. {topicmodels}, to parse topics from generated text would prolly be the way to go. Compare these topics to those in essays - however, longer essays may naturally have more overlap of themes.
Is topic modelling obsolete in the age of large language models?
open.substack.com/pub/language...
#largelanguagemodels #topicmodelling #topicmodels #topicmodeling #naturallanguageprocessing #machinelearning #computationallinguistics #LLMs #digitalhumanities
open.substack.com/pub/language...
#largelanguagemodels #topicmodelling #topicmodels #topicmodeling #naturallanguageprocessing #machinelearning #computationallinguistics #LLMs #digitalhumanities
Is topic modelling obsolete?
It wasn’t so long ago that topic modelling was all the rage, particularly in the digital humanities. Techniques like Latent Dirichlet Allocation (LDA), which can be used to unveil the hidden thematic ...
open.substack.com
May 10, 2025 at 12:15 PM
Is topic modelling obsolete in the age of large language models?
open.substack.com/pub/language...
#largelanguagemodels #topicmodelling #topicmodels #topicmodeling #naturallanguageprocessing #machinelearning #computationallinguistics #LLMs #digitalhumanities
open.substack.com/pub/language...
#largelanguagemodels #topicmodelling #topicmodels #topicmodeling #naturallanguageprocessing #machinelearning #computationallinguistics #LLMs #digitalhumanities
CRAN updates: censobr congress movMF nhanesA riskmetric topicmodels #rstats
January 9, 2024 at 4:02 PM
CRAN updates: censobr congress movMF nhanesA riskmetric topicmodels #rstats
.#BSwallow & #EBayer @ #MDurrett et al @ #dayofdh18cc: #topicmodeling of Latin texts = took wks. So for comps / to fill time, they built AWESOME #FOSS app to visualize #topicmodels. http://cs.carleton.edu/cs_comps/1718/latin/final-results/the-app.html #loquela CC @dighall @nolauren...
December 6, 2024 at 9:12 AM
.#BSwallow & #EBayer @ #MDurrett et al @ #dayofdh18cc: #topicmodeling of Latin texts = took wks. So for comps / to fill time, they built AWESOME #FOSS app to visualize #topicmodels. http://cs.carleton.edu/cs_comps/1718/latin/final-results/the-app.html #loquela CC @dighall @nolauren...
Updates on CRAN: topicmodels (0.2-17)
August 14, 2024 at 5:16 AM
Updates on CRAN: topicmodels (0.2-17)
Updates on CRAN: PReMiuM (3.2.13), PRIMME (3.2-6), pttstability (1.4), PUPMCR (0.2.0), REDCapCAST (24.1.1), reddPrec (2.0.0), riskmetric (0.2.4), sbtools (1.3.1), SenSpe (1.3), tglkmeans (0.5.4), topicmodels (0.2-16), weibullness (1.24.1)
January 9, 2024 at 5:17 PM
Updates on CRAN: PReMiuM (3.2.13), PRIMME (3.2-6), pttstability (1.4), PUPMCR (0.2.0), REDCapCAST (24.1.1), reddPrec (2.0.0), riskmetric (0.2.4), sbtools (1.3.1), SenSpe (1.3), tglkmeans (0.5.4), topicmodels (0.2-16), weibullness (1.24.1)
Noen her på twitter som har peiling på #TopicModels og har lyst til å kode noe basert på @Nasjonalbibl’s API? #uibeta #digitalhumaniora
November 8, 2024 at 9:31 AM
Noen her på twitter som har peiling på #TopicModels og har lyst til å kode noe basert på @Nasjonalbibl’s API? #uibeta #digitalhumaniora
Noen i feeden min som har brukt gensim? #TopicModels
November 8, 2024 at 8:29 AM
Noen i feeden min som har brukt gensim? #TopicModels
If it's something like topic extraction that you would like to do then perhaps something like this could be useful: cran.r-project.org/web/packages...
(I have not done LDA in R before so have not tried out this package)
(I have not done LDA in R before so have not tried out this package)
topicmodels: Topic Models
Provides an interface to the C code for Latent Dirichlet Allocation (LDA) models and Correlated Topics Models (CTM) by David M. Blei and co-authors and the C++ code for fitting LDA models using Gibbs ...
cran.r-project.org
June 7, 2024 at 8:12 AM
If it's something like topic extraction that you would like to do then perhaps something like this could be useful: cran.r-project.org/web/packages...
(I have not done LDA in R before so have not tried out this package)
(I have not done LDA in R before so have not tried out this package)
Tough questions, nice insights!
Thanks Manuel Couto for sharing your #PhD work in today’s #DoctoralMeeting: a study on social media content mining to detect early psychological risks using #TopicModels & temporal embeddings
🔗 s.citius.gal/dmmanuelcouto
#RedeCiGUS #FondosEuropeos
#AI #MentalHealth
Thanks Manuel Couto for sharing your #PhD work in today’s #DoctoralMeeting: a study on social media content mining to detect early psychological risks using #TopicModels & temporal embeddings
🔗 s.citius.gal/dmmanuelcouto
#RedeCiGUS #FondosEuropeos
#AI #MentalHealth
May 16, 2025 at 8:57 AM
Tough questions, nice insights!
Thanks Manuel Couto for sharing your #PhD work in today’s #DoctoralMeeting: a study on social media content mining to detect early psychological risks using #TopicModels & temporal embeddings
🔗 s.citius.gal/dmmanuelcouto
#RedeCiGUS #FondosEuropeos
#AI #MentalHealth
Thanks Manuel Couto for sharing your #PhD work in today’s #DoctoralMeeting: a study on social media content mining to detect early psychological risks using #TopicModels & temporal embeddings
🔗 s.citius.gal/dmmanuelcouto
#RedeCiGUS #FondosEuropeos
#AI #MentalHealth
🆕 #rstats tutorial: Qualitative analysis for big data: tidytext and topicmodels https://doi.org/10.31234/osf.io/x2nf5_v1
OSF
osf.io
February 25, 2025 at 1:25 PM
🆕 #rstats tutorial: Qualitative analysis for big data: tidytext and topicmodels https://doi.org/10.31234/osf.io/x2nf5_v1