PDF Publication Title:
Text from PDF Page: 166
142 year are revealed. This is because the precision is defined based on the number of unrevealed users, which becomes much smaller as significant fractions are revealed. We now turn back to Figure 7.3 and discuss each attribute in detail. 1.00 0.80 0.60 0.40 0.20 0.00 1.00 0.80 0.60 0.40 0.20 0.00 Figure 7.4 : Recall and precision for matriculation year community detection for Rice undergraduates for our algorithm. Individual lines are shown for each matriculation year. Certain values of user attributes are easier to detect than others. Colleges: The results show that colleges can be inferred with very high recall and precision by both our algorithm and the algorithm of Luo when as few as 10% of the students in the college are known. For example, when 20% of the members of a single college are provided to the algorithms, both our algorithm at that of Luo can infer over 80% of the remaining members of that college with over 95% accuracy. Figure 7.5 shows this in detail for our algorithm, focusing on the performance when Freshmen Juniors Sophomores Seniors 0 0.2 0.4 0.6 0.8 1 Fraction of Users Revealed Recall PrecisionPDF Image | Online Social Networks: Measurement, Analysis, and Applications to Distributed Information Systems
PDF Search Title:
Online Social Networks: Measurement, Analysis, and Applications to Distributed Information SystemsOriginal File Name Searched:
SocialNetworks-Thesis.pdfDIY PDF Search: Google It | Yahoo | Bing
Cruise Ship Reviews | Luxury Resort | Jet | Yacht | and Travel Tech More Info
Cruising Review Topics and Articles More Info
Software based on Filemaker for the travel industry More Info
The Burgenstock Resort: Reviews on CruisingReview website... More Info
Resort Reviews: World Class resorts... More Info
The Riffelalp Resort: Reviews on CruisingReview website... More Info
| CONTACT TEL: 608-238-6001 Email: greg@cruisingreview.com | RSS | AMP |