TAAG is focused on bringing the power of text analytics to bear in the accounting domain. Our research team specializes in applying automated text analysis techniques to gain insights into a company: going far beyond the limits of what can be observed from financial data alone. Our results benefit from having a multi-disciplinary approach, with team members experienced in the fields of accounting, auditing, computational linguistics, communications, finance, and computer science.
TAAG's dual missions are to advance scientific knowledge and to inform industry and policy at the intersection of text analytics and accounitng.
TAAG Text Mining Tools
l Structured Programming for Linguistic Cue
Extraction
<ahref="http://splice.cmi.arizona.edu">(SPLICE)</a>
A web-based research tool for calculating linguistic cue values based on dictionaries, part-of-speech tagging, indices, and other parsing techniques.
l Linguistic Inquiry and Word Count
<ahref="http://www.LIWC.net">(LIWC)</a>
A
research tool for calculated linguistic cue values based on dictionaries and
other parsing techniques.
l Used Visual Basic to write parsing programs etc.
l Weka
l Cluto
l Visual Basic
l Python
l Natural Language Tool Kit (NLTK)
l IBM Data Modeler
l CMU Toolki
Links:
[1] http://splice.cmi.arizona.edu
[2] http://www.LIWC.net
[3] http://business.rutgers.edu/faculty-research/directory/moffitt-kevin
[4] http://business.rutgers.edu/faculty-research/directory/vasarhelyi-miklos
[5] http://ww2.ramapo.edu/asb/faculty/Chakraborty.aspx
[6] https://raw.rutgers.edu/students/bochkay
[7] https://raw.rutgers.edu/students/chychyla
[8] http://business.rutgers.edu/faculty-research/directory/hussein-issa
[9] https://raw.rutgers.edu/students/liu
[10] https://raw.rutgers.edu/students/yoon