Predicting author blog channels with high value future posts for monitoring

TitlePredicting author blog channels with high value future posts for monitoring
Publication TypeJournal Articles
Year of Publication2011
AuthorsWu S, Elsayed T, Rand W, Raschid L
JournalProceedings of the Twenty-Fifth Conference on Artificial Intelligence (AAAI)
Date Published2011///

The phenomenal growth of social media, both in scale andimportance, has created a unique opportunity to track infor-
mation diffusion and the spread of influence, but can also
make efficient tracking difficult. Given data streams rep-
resenting blog posts on multiple blog channels and a focal
query post on some topic of interest, our objective is to pre-
dict which of those channels are most likely to contain a fu-
ture post that is relevant, or similar, to the focal query post.
We denote this task as the future author prediction problem
(FAPP). This problem has applications in information diffu-
sion for brand monitoring and blog channel personalization
and recommendation. We develop prediction methods in-
spired by (naıve) information retrieval approaches that use
historical posts in the blog channel for prediction. We also
train a ranking support vector machine (SVM) to solve the
problem. We evaluate our methods on an extensive social
media dataset; despite the difficulty of the task, all methods
perform reasonably well. Results show that ranking SVM
prediction can exploit blog channel and diffusion characteris-
tics to improve prediction accuracy. Moreover, it is surpris-
ingly good for prediction in emerging topics and identifying
inconsistent authors.