DATA Mining – A Social Scientist’s Tools: ELAN and Praat

If one considers doing serious field and/or ethnographic work in social, interactional and behavioural sciences, one should consider getting acquainted with the softwares Elan developed by the Max Planck Institute for Psycholinguistics, Nijmegen (MPI Nijmegen henceforth), and Praat by (Boersma and Weenink, 2014).

In my doctoral work, I produced micro-analytic and multi-layered transcripts of Interactional sequences and organised them in a database with the help of ELAN.

Source: Albanese, C. "Composite Semiotics of Interactional Repair in French and Italian TV Debates"

Source: Albanese, C. “Composite Semiotics of Interactional Repair in French and Italian TV Debates”

 

Praat was then used to analyse intonational aspects of talk such as pitch, frequency, energy. These features are  automatically extracted by the software.

Source: Albanese, C. "Composite Semiotics of Interactional Repair in French and Italian TV Debates"

Source: Albanese, C. “Composite Semiotics of Interactional Repair in French and Italian TV Debates”

ELAN and Praat work very well together and allow for exchanging different databases and files types. Material on how to learn using the software is widely available online and both teams of developers are very responsive to customers’ inquiries.

Note: the software don’t transcribe content for you. You may try using another software for that but in my experience the result is not the best if you need high quality micro-interactional transcription.

Tip: Start in ELAN with automated segmentation. Then add linguistic (and other categorical) content manually. A researcher or – better – more researchers’ eyes are always needed when dealing with human data and social disciplines in general.

Leave a Reply