I am looking for an open source library for Linguistic Inquiry and Word Count (LIWC). Something in java or python will be good, though I am open to use other language.
Does anyone know where I can get one ?
Cheers,
The main benefit of the LIWC software is access to the LIWC data, which isn't open source.
LIWC is an extremely affordable software tool. LIWClite7 is $30 USD while LIWC2007, the full version, is $90 USD. (When compared to shareware text analysis software, this is not cheap.
LIWC reads a given text and compares each word in the text to the list of dictionary words and calculates the percentage of total words in the text that match each of the dictionary categories.
LIWC is considered the gold-standard of psychology-based NLP; it has over 19,000 research citations spanning a broad range of domains including insider threat, deception, relationship initiation and stability, political survival strategies, dementia detection and more.
As ealdent points out, LIWC is both software and a data set. The data set is proprietary so there is no open-source version of that. For the software side, TAWC is a useful open source Perl version. From the comments:
This is a semi-complicated script adapted from the one used in my CHI papers. The task of this script is to read in regular expressions from a dictionary (or if they're not REs, to make them into REs), which must be backwards-compatible with the LIWC software set (c.f. http://www.liwc.net). It then counts the number of matches for the RE in a single input row / user, and outputs it for that row / user.
You could then buy LIWClite which is less than half the cost of LIWC. You can also use TAWC with your own dictionaries for free.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With