This is a free non-commercial open source software!
2.0.0
[New features] We add sentiment analysis, which is useful for determining the emotional tone of a piece of text, such as a customer review or social media comment.
[New features] We add Shifterator, which is useful for visualizing pairwise comparisons between texts through word shifts.
[New features] We add WordCloud, which is a simple yet powerful way to see which words appear most often in a collection of text.
[Interface] Some adjustments are needed to make it easier to move from one menu to another.
[Data Source] Now supports PubMed Central Article Datasets (.tar.gz or .xml). Please visit PMC.
[Data Source] Now supports HathiTrust's JSON file. Please visit HathiTrust.
[Data Source] Now supports Dimension's CSV file. Please visit Dimension.
[Data Source] Now supports OpenAlex's CSV file. Please visit OpenAlex.
[Data Source] Now supports XLS and XLSX files.
[Topic Modeling] New option in pyLDA that allows you to adjust the Lambda, and you can now download the results as a file.
[Topic Modeling] Enables fine-tuning of topic representations using a KeyBERT-like model, supported by large language models such as OpenAI’s GPT-4o or Google’s Flan-T5.
[Burst Detection] Fix the issue on the visualization and now support n-grams.
[Sunburst] Support filter by citation or certain text and focus on a specific source.
1.1.1
[Enhancement] Adding the option to choose term frequency or document frequency for burst detection.
1.1.0
[New features] We added burst detection and scattertext to accompany your analysis.
[Interface] All new interface! Now you can navigate easily through the app.
1.0.1
[New feature] Check your data before starting analysis. Please check the File Checker.
[Keywords Stem] On the list of keywords, you will see the yellow color for each keyword that has the same result.
[Topic Modeling] No need to change your column name for topic modeling. You can choose the preferred column directly from the app.
[Bidirected Network] Too many nodes? You are now able to choose only the nodes you want to visualize.
1.0.0
We now support The Lens's CSV file. Please visit Lens.org.
We're moving to HF Spaces with CPU basic (2 vCPU and 16 GB RAM).