TextAnalyzer

What TextAnalyzer is

TextAnalyzer is a free web tool for analyzing English text data. It combines open-source lexica for lexical analysis and can compute topic models using latent Dirichlet allocation. Upload a CSV or XLSX file with an ID column followed by a text column; additional columns are ignored. Text is tokenized with the NLTK tokenizer, and results come back as a tabular file with a score column for each lexicon category. Available features include Flesch-Kincaid grade level, concreteness, familiarity, emotionality, and pronoun frequencies. The NRC Hashtag Emotion and Sentiment lexicon covers anger, anticipation, disgust, fear, joy, sadness, surprise, trust, and positive and negative sentiment. An optional Age & Gender lexicon produces predictions about the text author's age and gender. TextAnalyzer was founded in 2020 and is provided by Jonah Berger, Garrick Sherman, and Lyle Ungar of the University of Pennsylvania. Its Free plan costs nothing. Comments, suggestions, and bug reports can be sent to [email protected].

Who it suits

TextAnalyzer suits researchers working with English text who want lexical measures or topic models from CSV or XLSX uploads. Its optional Age & Gender lexicon may be relevant to users seeking those text-based predictions.

Getting started

1. Visit https://textanalyzer.org/.
2. Prepare a CSV or XLSX file with an ID column followed by a text column.
3. Upload the file for analysis.
4. Review the returned tabular file of category scores.

Verdict

TextAnalyzer provides a set of lexical measures and topic modeling for English text uploads, with results delivered as a tabular file. Its accepted input structure is specific: an ID column followed by a text column.