earticle

영어

Nowadays, increasing number of people prefer to shop online which has become a central part in their daily life. However, this precipitates a need to get knowledge about how people show their interests in the product which may contribute to recommend the right product for them. In this paper, an experiment was conducted in a clothing website which aimed to find out how and when people were interested in certain product in terms of eye movement and browsing behaviour. The results show that for eye movement, there is no direct relationship between pupil diameter and interests, and user’s interests have direct correlativity with blink frequency for some users. Moreover, eye movement can predict the user’s interests, and the accuracy is about 62%; for browsing behaviour, scroll times and display time also has something to do with the user’s interest; as for the relationship between eye movement and interactive behaviour, when scroll times increases, then saccade will increases too, but fixation time will reduce. Therefore, the conclusion can be drawn that when users shop online, they always need to interact with online store, and eye movement and interactive behaviour occurs in a particular pattern. This result could contribute to choose the corresponding parameters for recommendation and avoid using the parameters which can reflect users’ interests in the same degree or choose the one which can reflect users’ interest effectively to greatest extent.