WordStat versions

v7.0 [Dec 18, 2014]
Topic Extraction Tool:
- A new topic modelling tool based on factor analysis has been implemented to quickly extract topics from large collections of documents. Obtained topics may be renamed, merged, or deleted. A side panel also allows one to compare the frequency of specific topics across other variables using bar charts or line charts.
Link Analysis Feature:
- A new Link Analysis feature allows one to display co-occurrence data using force-based graphs, multi-dimensional scaling or circular graphs. Graphs are interactive and may be used to explore connections and to retrieve text segments associated with specific connections.
Named Entity Extraction:
- A new pattern-based named entity extraction feature has been added. Extracted names may be added to the categorization dictionary using drag-and-drop operations.
Improved Dendrogram Page:
- When clustering keywords or content categories, a new panel on the right of the dendrogram displays the frequency distribution of the selected cluster across up to two independent variables as well as a link chart.
More Intelligent Handling of Misspellings:
- Misspellings and unknown words are now automatically matched with existing entries in the user dictionary and may be quickly added to such dictionary. The redesigned interface also identifies potential replacements as well as possible misspellings of words that are part of phrases currently in the categorization dictionary.
Improved Keyword-In-Context Feature:
- The KWIC (Keyword-in-Context) page now includes a tree view of the keyword contextual data sorted in descending order of frequency. The tree view may be used to easily filter and navigate through long concordance lists.
Improved Drag-and-Drop Editing:
- One can now drag suggested words (Frequencies page) and overlapping phrases (Phrase Finder page) directly from the right-most panels to the dictionary panel (left-most panel).
More powerful Proximity rules:
- The Rule Editor now supports up to four conditions, and each of those conditions can use a different distance setting in terms of units (document, paragraph, sentence, etc.) and physical distance (number of words).
Stemming in 18 languages:
- Fast stemming has been implemented for 18 languages (English, French, Spanish, Basque, Catalan, Czech, Italian, German, Danish, Dutch, Finnish, Hungarian, Norwegian, Portuguese, Romanian, Russian, and Swedish)
Viewe and edit the Automatic Replacement list:
- One can now review the automatic word replacement list, edit entries, as well as import and export this list to disk, allowing one to share the list of replacements with other users or to move it to another computer.
Log of changes in dictionaries:
- A log of all changes made to categorization dictionaries and exclusion lists is now stored on disk. This feature may be disabled, if necessary.
Import and export categorization dictionaries:
- Dictionaries may now be imported from, or exported to Excel, tab or comma-delimited files, and XML files.
Speed improvements:
- Several speed improvements have been made. For example, the phrase extraction tool is now from five to 20 times faster, and computing a KWIC list on large data sets, which used to take several minutes to extract, now takes a fraction of a second and more.