Your聽eyes might give away how well those French lessons are really going. By monitoring the unconscious eye movements of someone as they read, an algorithm is able to work out how proficient they are.聽The technology could one day help create more personalised online learning tools.
Current language tests have several drawbacks. Students may receive training to pass a specific exam, for example, which may not reflect their overall knowledge of the language. Instead, from the Massachusetts Institute of Technology and his colleagues were keen to see if tiny eye movements could be an alternate way of evaluating language ability.
Using an eye tracker mounted on a desktop, the team tried to determine the competency of 145 English language students by recording their eye movements while reading a series of standalone sentences. The length of time聽each person would fix their gaze on different words and transition to the next word were measured, for example.聽聽Their results were compared to 37 native speakers who performed the same exercise.
Advertisement
Parlez-vous fran莽ais?
The gaze of聽the learners and native speakers were compared and an聽algorithm then estimated the learners鈥� language proficiency score based on their eye data alone. The estimate was checked against their previous results on two standardised language tests. The team found that there was a pretty good聽correlation between eye movements and reading proficiency.
from Lancaster University in the UK thinks the approach is promising. However found that although eye movements could provide information about some aspects of reading, such as the ability to decode words, they revealed little about higher level processes such as extracting key information from a longer passage.聽 鈥淓ye movement data聽might provide useful聽complementary聽information in second language聽reading assessment,鈥� she says.
Berzak and his colleagues are currently developing a tool to gauge a person鈥檚 abilities while they are reading online, using eye-tracking software and a device鈥檚 built in camera. Text could then be modified to match an individual鈥檚 level, catering to both second language and native speakers. 鈥�
鈥淯nprecedented amounts of text are presented to users in digital form,鈥� says Berzak. 鈥淚t would be highly beneficial to personalise its complexity and content.鈥�
搁别蹿别谤别苍肠别:听arxiv.org/abs/1804.07329
