‘According to results of their own research, (the system) helped to improve the detection-rate of forged text from 54 percent to 72 percent’
Computer generated text has ‘tells’ that distinguish it from human writing, reports THE DAILY MAIL. Researchers at Harvard and MIT found that computers are more likely to use predictable words. The findings could help flag fake texts.
- Researchers parsed texts and coded the results using colours, green for ‘predictable’ and other colours for less obvious words. Computer-generated text shows up as a higher ratio of green. Human writing shows up as a balanced mixture.
- Language used by humans tends to be more unconventional, either in individual word choices or how they are arranged in a phrase or sentence.
The researchers say their system works on smaller texts and is not intended for a large scale. The project concentrated on text and not video.
SEE RELATED STORY
This AI tool is smart enough to spot AI-generated articles and tweets TNW | July 29, 2019 | by Ravie Lakshmanan |‘Initiatives like (this) can be valuable not only in detecting fake text, but also identifying Twitter bots that have been used to disrupt electoral processes in the US and elsewhere.’