Viterbi creates program used to analyze online text

The Viterbi School of Engineering and the Dornsife College of Letters, Arts and Sciences has teamed up under Morteza Dehghani, assistant professor of psychology and computer science, to create Text Analysis, Crawling and Interpretation Tool.

TACIT allows research psychologists to analyze text from online sources, such as social media profiles. Its architecture allows use of multiple plugins, which will make textual analysis easier for researchers.

“Currently [text analysis] techniques are available as independent programs or software, but they require a lot of expertise and because social scientists often don’t have the programming background, they don’t use them,” Dehghani told USC News. “So we’ve created a very researcher-friendly environment where they can easily access and use these methods. And if they want more, anyone can write their own plugins for the system.”

This program has seen success internationally in the past year and a half because it is user-friendly and allows researchers to mold the program to their studies.

“In the first week the program launched there were over 2,500 hits to our website,” Dehghani told USC News. “We had people from Kenya to Vietnam, from Uruguay to Estonia and from Hawaii to Maine downloading the software.”

There are three primary components to the TACIT system: automated text collection, which parses through websites related to the computational linguistic or psychological study, storage and processing of formal bodies of text and the creation of data points for analysis.

TACIT required collaboration from psychological doctoral students Kate Johnson and Joe Hoover and eight computer scientists from the computer science department.

This program has many real-world applications apart from research. Health psychologists can use TACIT to prevent early signs of depression and suicide.

Since the advent of computers, textual analysis in the world of psychology has been growing rapidly, and with TACIT, USC remains ahead of the curve.

Leave a Reply