TexLexAn blog

I open a new blog exclusively for TexLexAn. The link: http://texlexan.blogspot.com/

I will report the development news exclusively on telexan.blogspot.

Sentiment analysis - Text mining

A new feature is added to TexLexAn. The version 0.34 ( texlexan CLI 0.34 + texlexan GUI 0.30 ) is able to estimate the sentiment polarity and to evaluate the intensity of the sentiment in the text.

The sentiment analysis is based on a knowledge base and a simple lexical analyser. The analyser returns a global rating of the sentiment in the text and extracts each sentence expressing a sentiment.

This program runs under Linux and FreeBSD and is available on sourceforge:
http://sourceforge.net/projects/texlexan/files/

In present time, only English and French languages are implemented. There are two only dictionaries: keyworder.en.dicE and keyworder.fr.dicE in the package (pack 1.42); they are very incomplete and contain only 80 words expressing a sentiment. I will explain in another post how to complete these dictionaries.

ImagEmovie 0.8 is released

It is now possible to add one effect for each slide (image or movie). The effects available are limited to the blurring, shaking, contour, random pixels and saturation-brightness changes. Les effects, transitions and text animations are provided by plugins, new ones will be added in the future.

ImagEmovie 0.8 code source and debian package are available on Sourceforge.

ImagEmovie 0.7-0 sound effects

This new release of ImagEmovie allows to attach the audio file to slide, and to add several effects such as the echo, reverberation, chorus, phasing and fading.

The is basic web site about ImagEmovie, providing some explanations how to install the packages or how to use the Ken Burns effects: http://imagemovie.sourceforge.net/

ImagEmovie 0.5-1

This new version allows multiple videos inside the slideshow and some basic text effects for the videos inserted.

Exemple of slideshow: http://www.youtube.com/watch?v=GvXUcFU5qTc

Program: http://sourceforge.net/projects/imagemovie/

Make a movie from your pictures

ImagEmovie is the name of project that allows to create a movie from simple pictures.
The program is available in sourceforge: https://sourceforge.net/projects/imagemovie/

It's possible to add transition between two pictures, insert animated text and perhaps the most interesting, it the possibility to zoom and pan along the picture with the Ken Burns effect.

You can view an example of video posted on youtube here: http://www.youtube.com/watch?v=CQlLqhJxtO4

ImagEmovie requires GTK, Cairo, FFMPEG and SOX

Open Source Summarizer for Linux TexLexAn 0.30

The project is jumping to the alpha status. All the functionalities are implemented. Now, the codes is going to be optimized and debugged and new languages will be added to the summarizer. The current version accepts English, French and Spanish.

- The linear classifier use the perceptron method.
- The summarizer uses its past experiences to select the best summarizing method.

The webpage: http://texlexan.sourceforge.net

The code: http://sourceforge.net/projects/texlexan/

The automatic Summarizer and the deadwood Expressions.

The deadwood expressions and some adverbs fill the text of unnecessary words. They can be removed without a significant lost of information. Sentences between brackets provide some extra information / explanations; but the redundancy they give are not necessary in a summary.

- The next version of the summarizer TexLexan will include a function to replace the dead wood expressions with single word or simplified expressions. The result will not extraordinary in term of compression (about 5 to 10%) but will make the summaries easier to read.

- The sentences between brackets will be suppressed too.

- Some combinations of adverbs or adjectives will simplified. For instance, the adverb 'very' can be often omited without changing the meaning of a sentence.

Web page summarizer for Linux

It's now possible to summarize a web page with TexLexAn (Linux/FreeBSD).

It's pretty simple to use: Open TexLexAn, you will have a small window in the top of your desktop, and from your web browser (Firefox, Opera...) just drag'n drop the link into TexLexAn, click OK and wait a couple of second to couple of minutes (it's depending of the size of page to download) to get a summary (extracts more precisely) of the page.

TexLexAn summarizes text, html, doc, pdf, ppt and odt documents (doc,pdf,ppt and odt and requires the small programs antiword, pdftotext, ppthtml and odt2txt).

- About the TexLexAn project in French, go here: http://sansmicrosoft.canalblog.com/archives/2009/03/30/13190006.html

- You can download the program there: http://sourceforge.net/projects/texlexan/

Automatic Text Analyzer Classifier Summarizer

TexLexAn is an Automatic Text Analyzer Classifier Summarizer with a half-supervized learning ability. These programs are still in development but functionnal.

The first package as been released today and can be dowloaded from my other blog: download

Look at the screenshoots: