This website doesn't use cookies to identify you. (More info)
en es fr it

PRODUCT / News (trial, release history)

T-LAB Plus 2016 was released on April 22nd 2016. (New: T-LAB Plus 2018 released)

Listed below are some of the key improvements and new features:

1 - Now eleven different file formats - including PDF documents - can be processed either as a single file or as a collection of documents.

- The image-only PDF files must be processed using OCR software first;
- HTML files can be imported by using the Corpus Builder module only.

2 - Two user profiles are now available: beginner and expert. When the first (i.e. beginner) is selected, the user is allowed to perform any analysis without being asked to choose between the advanced options.

3 - Whenever analysing word co-occurrences and/or exploring clustering solutions, a new tool named Graph Maker allows the user to easily create and export several new dynamic charts and graphs, some of which are built with the D3 library.

4 - Every time a tool for exploring similarities and differences between corpus subsets or between thematic clusters is used a new button is available which allows the user to view a preview by means of a dynamic tree map.

5 - An additional algorithm for the thematic analysis (i.e. unsupervised clustering) of text segments and documents is now available which complements the bisecting Kmeans algorithm implemented in T-LAB more than ten years ago.
The new algorithm uses the PDDP (i.e. Principal Direction Divisive Partitioning) method proposed by Daniel Boley (1998) to initialize a k-means clustering procedure.

This way the user of T-LAB with an expert profile is able to compare different solutions for the same clustering problem, e.g. compare the quality of clusters obtained by two different algorithms applied to the same data tables.

T-LAB Plus was released on September 14th 2015.

T-LAB Plus is a new software product which results from re-engineering the latest version of T-LAB 9.1 and paves the way for further developments.

Below is a short table which summarizes the key improvements:

  T-LAB Plus 2015 T-LAB 9.1
Input format texts in all languages,
including those using ideograms
(i.e. txt files in UTF-8 format)

texts in Latin characters only
(i.e. txt files in ASCII/ANSI format)

Maximum size of a corpus

90 MB
(i.e. about 55,000 pages in .txt format)

30 MB
(i.e. about 18,000 pages in .txt format)

- Chinese, Japanese and a few other languages often have no delimiters (i.e. blank spaces and/or punctuation marks) between words. When this is the case, before importing any text with
T-LAB Plus, the user will need to perform a text segmentation first, by using other software which are usually available for free and they are different for each language (see

- The two versions of
T-LAB use two different database engines; consequently, the analysis projects carried out with T-LAB 9.1 cannot be directly imported into T-LAB Plus (and viceversa).

Among a great deal of new features, below is a short list of the most important:

  • A new powerful and very flexible tool named Text Screening allows the user to easily edit any corpus, create word lists, check customizable n-grams and/or word environments (i.e. word spans), as well as import/use customized multiword lists;

  • When importing a corpus in a language for which - at the moment - T-LAB Plus doesn't provide the automatic lemmatization (i.e. a language different from English, French, German, Italian, Portuguese and Spanish), the users are allowed to select/use stop word lists in twenty five languages and such lists, like the key-word lists and the multiword lists can be easily customized;

  • All tools for managing key-word list, for customizing dictionaries and for generating concordances (i.e. key-word-in-context outputs) are now integrated with each other and much easier to use;

  • Many new options are available by right-clicking on the tables;

  • Several analysis tools allow the user to create new dendrograms showing similarity relationships between key-words;

  • Several analysis tools allow the user to map the relationships between main themes either by using the MDS (i.e. Multidimensional Scaling) or the Correspondence Analysis method;

  • All tools for Correspondence Analysis include a button which allows the user to perform a Cluster Analysis with different methods;

  • The algorithms for automatic lemmatization and key-word selection have been improved;

  • The majority of the analysis tools have a new layout.

Here are some screenshots to allow you to better appreciate some new features of T-LAB Plus.

1- Three outputs obtained by analyzing Chinese, Russian and Arabic texts respectively:

2 - Using the Text Screening tool:

3 - Working with Stop-Word lists different from those available for the six languages which T-LAB can treat by automatic lemmatization (i.e. English, French, German, Italian, Portuguese and Spanish)

4- The integrated tools for key-word selection and dictionary building

5 - New options with right-click

6- New dendrogram options

7- Mapping themes/topics

8 - From Correspondence Analysis to Cluster Analysis

9 - New layout of the T-LAB tools (e.g. Specificity Analysis)

T-LAB 9.1 was released on March 14th 2014.

The most important improvements concern the Thematic Analysis tools.

More specifically:

- when the entire corpus can be considered like a discourse and/or its various sections (e.g. chapters of a book, parts of an interview, turns in a conversation or a debate, etc.) follow each other in a temporal order, the Thematic Analysis of Elementary Contexts tool allows the user to explore sequential relationships between themes, either by means of static charts and tables or by means of animated charts showing changes over time. This way the user can check either when people are engaged in specific themes (e.g. by looking at a diagonal of the matrix below) or when they shift from a dominant theme to another.

N.B.: The following picture and the animated charts below refer to a thematic analysis of The Politics of Climate Change (by Anthony Giddens) published on the T-LAB website.

- when using some thematic analysis tools (i.e. Modeling of Emerging Themes, Thematic Analysis of Elementary Contexts, Thematic Document Classification), by clicking the Quality Indices button (see below) it is possible to obtain a HTML file listing various measures which allow the user to assess the quality of the chosen partition and the semantic coherence of each theme.

- when performing a Thematic Document Classification and the analysis units (i.e. documents) are up to 3,000, by setting a T-LAB advanced option it is possible to obtain pairwise document similarities measures and so compare each document with all the others.

- when performing a thematic analysis of up to 3,000 analysis units (either text segments or documents), all data points can be plotted by means of the Correspondence Analysis tool (see below);


T-LAB 9.0 was released on October 14 2013.

Listed below are some of the key improvements and new features.

A new powerful and easy to use module named Corpus Builder has been added (see the pictures below) which allows easy transformation of any textual material into a corpus ready to be processed by T-LAB. Files in up to ten different formats can be quickly imported. In many cases the 'drag and drop' method is also allowed;

By using the Corpus Builder module the user is allowed to gather up to 30,000 texts; however, when using the 'Open Table' option and the text for each line doesn't exceed 2.000 characters (e.g. responses to open-ended questions, Twitter messages etc.) then up to 99.999 records can be processed;

The above software module includes a Variable Manager tool which allows the user to edit, load, save and change any coding scheme, even from a different corpus (see below);

The layout of the main menu has been changed and it is much more intuitive;

To fulfill the requests of many users, the automatic lemmatization of German texts has been implemented;

The tools for co-occurrence analysis have been improved in various ways.
The results of various types of analysis (see the Word Association, the Co-Word Analysis and the Sequence Analysis tools) can be easily exported in several formats which can be processed by many software packages for network analysis which are available for free (see the pictures below).


The are now six proximity indexes available and the Word Association tool also allows the user to analyse word-based n-grams as well as obtain second order measures which highlight similarities in meaning between key-terms (see the pictures below);

Several functionalities of the tools for comparative analysis have been improved. In particular, the Cluster Analysis tool now allows easy exploration of up to twenty partitions (see the picture below).

More options are available for creating a sub-corpus and for exporting data tables (see the picture below).

T-LAB 8.1 was released on September 24th 2012.

The most important improvements concern the Cluster Analysis tool, which is enabled after having performed any Correspondence Analysis (see the comparative analysis tools).

In detail:

- the Cluster Analysis tool now allows refining the results of Ward's hierarchical method by a K-Means algorithm (see the picture below);

- when clustering lexical units, tables with cluster characteristics contain further information (e.g. distances from centroids and Test Values);

- new charts are available which allow the user to better evaluate the relative contributions of each factorial axis to the clusters (N.B.: the same type of charts are now available also in the Thematic Analysis of Elementary Contexts and Thematic Document Classification tools);

Further improvements concern the possibility of importing/exporting customised word lists when using the Co-Word Analysis tool and when creating GraphML files by means of the Sequence Analysis tool.

T-LAB 8.0 was released on May 24th 2012.

The most remarkable improvements concern the possibility of integrating top-down (i.e. supervised) and bottom-up (i.e. unsupervised) approaches for the automatic classification of textual units like words, sentences, paragraphs and short documents.

In detail:

- a new tool for thematic analysis (i.e. Dictionary-Based Classification) accepts various types of inputs and allows the user to easily build/test/apply his models (e.g. his dictionaries of categories) both for 'classical' qualitative content analysis and for sentiment analysis.
All intermediate analysis stages can be easily verified and customised. The results (e.g. the tagged textual units) can then be exported and/or analysed by using others T-LAB tools;


- two of the most used T-LAB tools for thematic analysis (i.e. Thematic Analysis of Elementary Contexts and Thematic Document Classification) can now work either with an unsupervised or supervised method. This means that in the first case - like in the previous version of the software - they perform unsupervised clustering of textual units (i.e. they apply the bisecting K-means), whereas in the second case they perform supervised classification by using the same algorithm of the above mentioned new tool. Moreover, as dictionaries of categories can be easily imported and exported, users can now analyse various text collections by using the same criteria.

Other improvements include:

- now both the Co-occurrence Analysis and the Thematic Analysis tools can be used with lists of key-words (or semantic categories) that include up to 3,000 items (i.e. lists including about 7,000 distinct words);

- the Key Contexts of Thematic Words tool has been completely redesigned and now allows the user to work in two different way: either by selecting key-terms or by typing/pasting sample texts in an appropriate box. In both cases T-LAB uses the cosine measure and extracts all textual units (i.e. elementary contexts) which are most similar to the user's queries. In other words, it is possible to easily explore in which contexts the listed key-terms are used in as well as checking similarities between sentences, paragraphs or short documents;

- the Specificity Analysis tool, in addition to providing measures and charts which allow the user to check which lexical units (i.e. words or lemmas) are typical of or exclusive to specific corpus subsets, now allows the easy extraction of the characteristic fragments (i.e. elementary contexts) of each analysed subsets (e.g. the 'typical' sentences used by 'men' or 'women' in specific contexts). For this purpose T-LAB uses a normalized version of TF-IDF measure;

- the Contingency Tables tool now allows the user to export co-occurrence matrices with dimensions up to 1,500 x 1,500;

T-LAB 7.3 was released on October 6th 2011.

The most significant improvements are the following:

1 - Now all T-LAB charts obtained by Correspondence Analysis, including those concerning thematic clusters, allow the user to select each item (i.e. key-word or category) to be plotted: just right click on the charts and select the 'Add/Remove items' option (see below);

2 - All charts mentioned above allow the user to plot the analysis results either by using the coordinates or the squared cosines (i.e. measures which allow us to easily appreciate the correlation between the analysed items and factorial axes).

3 - Now all word relationships within the clusters obtained by a Thematic Analysis can be explored by mean of all the co-occurrence analysis tools which in T-LAB use statistical measures, including the Sequence Analysis tool which uses Markov chains as a sort of discourse analysis (see below);

N.B.: The above graph has been obtained by importing a .graphml file created by T-LAB through the Yed software available as a free download (see link ).

4 - A Variable Manager tool has been added which allows the user to rename and group both their variables and categories (see Variable Manager).

T-LAB 7.2 was released on September 14 2010.

The user interface has been completely revised in order to make text analysis more intuitive, productive and enjoyable.

Using T-LAB 7.2 you can now open multiple windows. This allows you to simultaneously display more outputs and interpret your data better.

Moreover you can explore multiple contingency tables and, by clicking specific items, you can create various charts and HTML files.

Here are some examples of the greatly improved functions of T-LAB 7.2.

For each analysis tool two links are available: to the corresponding section of the manual (HTML) and to a video demo which shows how it works (see below).


Word Association (Manual - Video)

Co-Word Analysis and Concept Mapping (Manual - Video)

Comparison between Word Pairs (Manual - Video)

Sequence Analysis (Manual - Video)

N.B.: By using all the above tools is now possible to check which words have been grouped into the same concept or lemma. Just click on an item of the corresponding table (see below).


Specificity Analysis (Manual - Video)

Correspondence Analysis (Manual - Video)

Cluster Analysis (Manual - Video)

Contingency Tables (Manual - Video)


Thematic Analysis of Elementary Contexts (Manual - Video)

Modeling of emerging Themes (Manual - Video)

Thematic Document Classification (Manual - Video)

In the new version all tables showed by T-LAB tools can be sorted in ascending and descending order just clicking any column heading.

Moreover each chart can be zoomed, maximized, customized and exported in different formats (just right click in order to show the popup menu).


Click here to learn more ..