LINGUIST List 14.1740

Thu Jun 19 2003

Software: Wordstat v4.0 & Codeminer 0.9 (Beta Version)

Editor for this issue: Tomoko Okuno <>


  1. Normand Peladeau, Wordstat v4.0: Analyzing Textual Information
  2. Normand Peladeau, Codeminer 0.9: Text Management & Qualitative Analysis

Message 1: Wordstat v4.0: Analyzing Textual Information

Date: Thu, 19 Jun 2003 22:30:55 +0000
From: Normand Peladeau <>
Subject: Wordstat v4.0: Analyzing Textual Information

Provalis Research is pleased to announce the release of WordStat version 4.0.

New features and improvements include:
-Dictionary moderated lemmatization and stemming (English only for
now, other languages will be added later).
-Heat map plot and dual-clustering to examining relationship between
keywords and categorical or numerical variables.
-Clustering and multidimensional scaling of cases (records or
documents) based on content similarity.
- Proximity plot to examine keywords co-occurrence or documents
similarity in descending order of similarity (limit of 5000
- Phrases finder to easily identify recurring phrases and idioms.
- New drag'n drop dictionary editor for easy and quick assignment of
words or phrases to dictionaries (may also be used to merge two
- Support for RTF documents (up to 10Mb per document) and larger memo
fields (beyond the previous 64Kb limit)
- Direct importation of Word, WordPerfect and HTML documents from the
- Customization of 2D and 3D multidimensional scaling charts,
correspondence plots and bar charts (title, color, data point, data
labels, etc.)
- Option to animate 3D multidimensional scaling charts and 3D
correspondence plots (allows better visualization of all 3
- Descriptions may now be assigned to dictionary categories.
- 3D barcharts and line charts.
- Weighting of words or phrases in content categories may now be
performed using floating-point numbers (positive values).
- Improved spell-checking with support for more than 10 different
languages such as English, French, Spanish, etc.
- All tables may now be saved in Excel, text or html format.
- All changes made to the categorization dictionary or exclusion list
may be canceled during a session.
- Automatic selection of inflected forms by suffix or WordNet
relationship (dictionary builder tool).
- Improve text editing (with undo).
- New categorization dictionaries based on WordNet and Roget ontology
- Miscellaneous changes, speed improvements, etc.

About WordStat: WordStat is a content analysis and text mining module
specifically designed to analyze textual information such as responses
to open-ended questions, interviews, titles, journal articles, public
speeches, electronic communications, etc. It provides numerous
statistical and graphical tools to visualize text and examine the
relationship between words or categories of words and the values of
categorical and numerical variables (cluster analysis,
multidimensional scaling, proximity plot, correspondence plot,
heatmap, bar chart, line chart, crosstabulation, statistical
association measures, etc.). Such tools allow users to compare how
different groups differs in vocabulary usage, discussed topic, or
content category. They also may be used to uncover existing
relationships between specific categories of words and numeric
variables such as age of the respondent, year of publication,
etc. WordStat can analyze text directly or apply categorization
dictionaries to group words with similar meanings. The program also
provides numerous tools to facilitate the development and validation
of new categorization dictionaries.

For more information on WordStat and to obtain evaluation copy please
visit our Web Site under:

Normand Peladeau
Provalis Research 
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue

Message 2: Codeminer 0.9: Text Management & Qualitative Analysis

Date: Thu, 19 Jun 2003 22:33:04 +0000
From: Normand Peladeau <>
Subject: Codeminer 0.9: Text Management & Qualitative Analysis


We are also working on a new text management and qualitative analysis
software. This new software will be offered as an optional base module
for WordStat. It will provide an easy way to manage documents and
perform common qualitative analysis tasks. While CodeMinder is still
under public beta testing, a pre-released version of CodeMiner is also

For more information on CodeMiner and to download a trial version,
please visit our web site at:

Normand Peladeau
Provalis Research 
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue