An Approach to Reading Assistance with Eye Tracking Data and Text Features

Unknown words and long and difficult sentences with complex structures often cause difficulties in reading comprehension. This paper proposed a reading assistance approach based on analyzing the eye tracking data and the text features of the gazed area in the process of reading. This approach could automatically detect the user's intention in terms of word translation or long sentence summary, and then display the meaning of the word or the summary of the sentences in the form of annotations. The pilot study results showed that the average accuracy of this approach reached 80.6%+/- 6.3%, and the automatically generated annotation improved the user's reading efficiency and subjective experience.