Authorial Voice Analyzer (AVA)
AVA is a natural language processing (NLP) tool for the analysis of interactional metadiscourse (authorial voice) features in texts. It generates various indices of stance and engagement features from Hyland's (2005) interactional metadiscourse model. Analyzing large text data (batch processing), it offers reliable, quantitative results for researchers and practitioners interested in the issues of reader-writer interaction and authorial voice strength.
ava_manual.pdf
File Size: 3673 kb
File Type: pdf
Download File
ava_measures.xlsx
File Size: 46 kb
File Type: xlsx
Download File
Yoon, H. (2017). Textual voice elements and voice strength in EFL argumentative writing. Assessing Writing, 32, 72-84.

Note. ​The current version of AVA runs on Mac OS X with up-to-date Java and python 2.7 or higher installed. To download the Java Development Kit (JDK), please visit here.

AVA is distributed under the terms of the GNU General Public License. 
Please email me if you have any questions or comments on the use of AVA.