Predicting the Difficulty Level of TED Videos by Readability Grade Level and Speed of Speech

Abstract

In order to use online multi-media for language education, one of the most important things is to know their difficulty level. We started a research project on how to predict the difficulty level of TED Talks. TED Talks are videos from expert speakers on education, business, science, technology and creativity, with subtitles. Each subtitle file has texts and timing data of speech, so we can easily calculate its readability grade level and speed of speech. We downloaded 205 TED Talk subtitle files from the website and analyzed 48,271 subtitles. It was found that TED Talk videos have various readability grade levels from 9th to 17th, 90% of them are in from 11th to 14th grade level, and cover a wide range of speed from 56 words per minute (wpm) to 211 wpm, 83% of them are in from 120 wpm to 180 wpm. In these results, we can conclude that you can estimate the difficulty level of TED videos by readability grade level and speed of speech. But it was also found that their levels and speech speeds are rather high or fast in the use of English language learning for Japanese students.