PROJECT TITLE :
Personal Web Revisitation by Context and Content Keywords with Relevance Feedback - 2017
ABSTRACT:
Obtaining back to previously viewed.Net pages may be a common nonetheless uneasy task for users because of the massive volume of personally accessed info on the internet. This paper leverages human's natural recall process of using episodic and semantic memory cues to facilitate recall, and presents a personal web revisitation technique known as WebPagePrev through context and content keywords. Underlying techniques for context and content recollections' acquisition, storage, decay, and utilization for page re-finding are mentioned. A relevance feedback mechanism is additionally concerned to tailor to individual's memory strength and revisitation habits. Our six-month user study shows that: (one) Compared with the prevailing.Net revisitation tool Memento, History List Searching method, and Search Engine methodology, the proposed WebPagePrev delivers the simplest re-finding quality find rate (ninety two.10 percent), average F1-live (0.4318), and average rank error (zero.3145). (2) Our dynamic management of context and content memories as well as decay and reinforcement strategy will mimic users' retrieval and recall mechanism. With relevance feedback, the finding rate of WebPagePrev increases by 9.eighty two p.c, average F1-measure will increase by 47.09 percent, and average rank error decreases by nineteen.forty four percent compared to stable memory management strategy. Among time, location, and activity context factors in WebPagePrev, activity is the best recall cue, and context+content based mostly re-finding delivers the best performance, compared to context primarily based re-finding and content primarily based re-finding.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here
