Behavior Modeling using Bigram Frequencies for Client-Side Link Prefetching

The perceived latency for a user surfing the Internet is the target of a transparent and speculative algorithm that relies on a user behavior model. The model is based on past user behavior and in combination with a weighting scheme for the outbound links of a particular web page, aims at reducing the perceived latencies. The assistance is in the form of prefetching some linked web pages and storing them in the browser's cache. A comparison between the proposed algorithms against two other prefetching algorithms yield improved cachehit rates given a moderate bandwidth overhead. Furthermore, the experimental results are proven to be statistically significant. KEY WORDS Pre-fetching, user behaviour modelling, bigrams

• Type: Conference
• Year: 2006
• Where: EUROIMSA
• Authors: Apostolos Georgakis, Haibo Li, Mihaela Gordan
• Keywords: EUROIMSA 2006, Multimedia, Past User Behavior, User Behavior, User Behavior Model