Loading...

Link Prediction in Complex Networks

Asghari, Mohammad | 2015

1804 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 47626 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Beigi, Hamid
  7. Abstract:
  8. With the growth of social networks, link prediction has attracted great attention. Completing partially observed networks, recognizing errors in observed links, predicting the network’s future structure to aid decision making, and presenting users with favorable links are some the motivations that have made link prediction important and effective for complex networks. In this work, we analyze link prediction in DBLP’s author network and attempt to increase the accuracy of state-of-the-art link prediction techniques by extracting discriminative information from the available metadata. Abstracts are an important resource that indicate an author’s field of study. Extracting the concepts an author has worked on and combining that with structural features derived from the network can improve link prediction accuracy significantly. To this end, we use a decision tree to classify similarity-based features. We then post-process the labels assigned by the decision tree using features derived from the available metadata. Experiments on the DBLP author network show that we are able to reduce false positive errors by half with only a small increase in false negatives. To the best of our knowledge, this work is the first to use the above features and post-process classifier decisions successfully
  9. Keywords:
  10. Topic Modeling ; Classification ; Link Prediction ; Similarity-based Algorithm ; DBLP Dataset

 Digital Object List

 Bookmark

...see more