The first application developed was for creating open cloze tests from Wikipedia articles (Wiki Tests). Initially this application was released as an android app and later an online service. An overview of the Wiki Tests app can be found here.
The next application to be developed was for analysing the Sentiment and Semantics of tweets. This application is available online and described here. A version for android will follow soon.
Recently I released another android app for learning Kanji, which can be downloaded for free from the Google Play Store. This app is intended for teaching English and is really a visual way of learning vocabulary.
These blogs contain material for anyone interested in the English language:
play store, help file). The online version is hosted on PythonAnywhere.
The Sentiment and Semantics online app (Android version to follow), allows you to view tweets containing the search phrase you enter when presented with a popup after pressing one of the update buttons. The tweets you view are classified according to their sentiment and can be analyzed with respect to their semantic content. Duplicates have been removed along with possible spam.
This application consists of three pages. A help page, a page which lists the kanji radicals along with their definitions and a page where you can interact with the main application for learning kanji.
A total of 2042 kanji are viewable and downloadable as a single file (Kanji List.txt). With this file you can look up each kanji by number and plan your lessons by deciding on the range of kanjis you would like to be displayed. For instance 1-10 or 11-20. You can also put the app in review mode and then test what you have learnt by viewing flash cards.
WSGI micro web-framework for Python called Bottle, hence the name. The GUIs for all apps were created with JQuery Mobile. All online apps are hosted by Pythonanywhere.Parallella micro server to take advantage of the parallel processing options available. Applications incorporating techniques from computational linguistics, especially vector semantics, can be very computationally intensive. The Parallella board provides a scalable platform for developing web applications requiring cutting edge performance.