The Fear Of AI Just Killed A Very Useful Tool https://www.techdirt.com/2023/08/08/the-fear-of-ai-just-killed-a-very-useful-tool/

Sounds like a really neat project - wish I'd known about it before, though then I'd be even more disappointed about it now 👎
#textanalysis

A great overview of different ways to analyse and visualise text: Text Visualization Browser https://textvis.lnu.se

Based on a review of academic paper. Not updated since 2019 but still a useful resource! #dataviz #textanalysis

Aos interessados em #textanalysis com discursos do legislativo, criei o pacote {notasTaq} em #RStats que estrutura notas taquigráficas de comissões do Senado em dataframe. O processo é simples, bastando fornecer o número da comissão.

#cienciapolitica

https://arxiv.org/pdf/2307.13106.pdf

How to use #largelanguagemodels #LLM for #textanalysis

"This guide introduces Large Language Models (LLM) as a highly versatile text analysis method within the #socialscience ... ranging from text annotation and classification to sentiment analysis and critical discourse analysis... using Python... analyzing the text, and validating the results... identifying populism in political texts, and show how LLMs move beyond the existing state-of-the-art"

Revisiting #VoyantTools, I just discovered in the docs that it has a concept of Skins, i.e., pre-defined combination of tools. https://voyant-tools.org/docs/#!/guide/skins That sounds great, but I can’t seem to find a way to switch skins. Any pointers? #DigitalHumanities #TextAnalysis

In my class on data visualization in the fall, I'll be introducing students to machine learning with text analysis. The first example uses album reviews to train a classifier by genre (rock, jazz, hip hop, folk). I contrast deductive (keyword coding) and inductive (token vectorization) approaches. The latter returns a classifier with 98% accuracy. This is the first LDA plot to demonstrate the classification.

#Sociology #Python #ComputationalSocialScience #MachineLearning #TextAnalysis

#AI #LLMs #Language #GenerativeAI #TextAnalysis: "James Zou at Stanford University in California and his colleagues have now tested whether the AI-detection tools worked equally well for all students. They did this by feeding a selection of essays to seven of the most popular AI-text detectors. “This is a pretty important problem,” says Zou.

In all, 161 essays, written in English, were given to each AI-detection service. Of those, 91 were written by people with English as a second language, obtained from a Chinese educational forum, and 70 were US college admission essays, mainly obtained from PrepScholar, an admissions preparation website.

Only about 5 per cent of the US-based essays were flagged as being written by AI, while, on average, 61 per cent of the Chinese essays were."

https://www.newscientist.com/article/2370080-tools-to-spot-ai-essays-show-bias-against-non-native-english-speakers/

5 Natural language processing libraries to use - Natural language processing libraries, including NLTK, spaCy, Sta... - https://cointelegraph.com/news/5-natural-language-processing-libraries-to-use #naturallanguageprocessing #languageunderstanding #textgeneration #nlplibraries #textanalysis

Content Similarity App: ready for testing!

1. Paste a list of phrases (keywords, product names, page titles, etc)
2. Select one to find the most similar items
3. Filter and narrow your criteria to get the most similar items
4. Export to CSV

App: http://bit.ly/42ZIG2Q

Sample data : https://bit.ly/40xZ0Xa (Zara UK/EN products, NYT cooking recipes, SEJ article titles)

#textanalysis #textmining #dataanalytics #contentmarketing #digitalmarketing #seo #plotly #frontend

RT @smitmartijn
I recently learned about #OpenAI's text moderation #API and that it's 🆓

Enabled it on some of sites that have user profiles and happy with the outcome!

Here's a quick blog post to understand how to use it with #PHP https://buff.ly/40FLZKE

#textmoderation #textanalysis #AI

I recently learned about #OpenAI's text moderation #API and that it's 🆓

Enabled it on some of sites that have user profiles and happy with the outcome!

Read my blog post to understand how to use it with #PHP https://lostdomain.org/2023/03/29/using-openai-free-content-moderation-api/

#textmoderation #textanalysis #AI

Code for Word Similarity is ready

Simple creative use of the document-term matrix data structure of @scikit_learn & a few manipulations & filtering.

Problem
For any document in a text list (corpus) give the most similar documents sorted by similarity (# of common words)

#SEO #DataScience #TextAnalysis #TextMining #Python

1/2

Word Similarity Matrix:

(following this post: https://seocommunity.social/@elias/110065714002693134)

Initial #Python code and quick overview can be found here:

https://linkedin.com/pulse/word-similarity-matrix-python-code-elias-dabbas/

#advertools #DigitalMarketing #DigitalAnalytics #TextAnalysis #TextMining #DataScience

Questions it might help answer:
▪️ Which phrase is the most unique (least common words with others)?
▪️ For each phrase sort all other phrases by similarity (simple search)
▪️ Simple recommendation engine: if you like this article "blue green red", you'll probably also like this one "blue green yellow". You probably won't like the article "magenta teal gray".

I'll share the initial #Python code for this soon.

Thoughts, feedback, suggestions?

#DataScience #TextAnalysis #DigitalMarketing #SEO #SEM

Word Similarity Matrix: first conceptual version

A very simple, no-mumbo-jumbo way of assessing how similar phrases* are to one other. Just count common words.

*Phrases:

▪️ Keywords
▪️ Title tags
▪️ Product names
▪️ Tweets or any social media posts
▪️ URLs
▪️ h1-h6 tags
▪️ Meta descriptions
▪️ Book titles
▪️ Product reviews

For each pair count how many common words they contain (count and fraction).

#DataScience #TextAnalysis #DigitalMarketing #SEO #SEM

“{corporaexplorer} is an #rstats 📦 that uses the Shiny graphical user interface framework for dynamic exploration of text collections.” By Kristian Lundby Gjerde.
https://kgjerde.github.io/corporaexplorer/
#RShiny #TextAnalysis

Sharing a quick post about TAGUETTE - a fantastic free open source solution for qualitative text analysis. Ill do a proper post on it once my site is up but yeah, get it, install it, try it out. Superb.
You can use an exe file to install on Windows, Mac needs a more technical approach but an installer is coming soon. You can also try it out online.

#research #academic #textanalysis #opensource #taguette

@politicalscience

The Summer School seeks to
👩‍💻 promote technical skills
💡 provide mentorship
😍 encourage networking and peer support for individuals identifying as women and non-binary, working with quantitative methods in Political Science and related disciplines

As every year, we offer a core program on #ComputationalMethods including Functions and #Programming in #RStats, #Visualization, #Webscraping, #TextAnalysis, and #ImagesAsData.

2/

When artworks are restituted, their provenances contains valuable information for researchers, historians and families.
Part of the series: Restitutions as Data. The Names In-between
https://www.openartdata.org/2023/02/tracking-looted-art-2-sothebys-sales-of.html
#GLAM #digitialhumanities #textanalysis #art #Holocaust #artlaw #Histodon #museum #provenance #arthistory

Automated scoring of reflective thinking in accounting students' writing "positively related to data analytics assignment grades [but] #emotionalIntelligence (EI) was not found to moderate th[is] relationship" (N = 86).

Images of pages from the thesis are attached: https://udallas-ir.tdl.org/handle/20.500.14026/2064

#CriticalThinking #Emotion #EmotionalIntelligence #EQ #NaturalLanguageProcessing #NLP #TextAnalysis #DevelopmentalPsychology #DevPsych #Teaching #Education #DataAnalysis