- Modeling twitter interaction behavior
We explore social interactions in Twitter, where we are focusing on getting a better understanding of what social interaction relations are, how long they last, what the actual interaction graph looks like and whether content is important when looking at interaction behaviors.
- Opinion Summarization for product review data
At the time of buying a new product (such as mobile, computer), it is usual to visit websites like Amazon or even turn to a web search engine to know what other consumers think about it. This method needs an important manual activity and turns into a long time. To solve this problem, we want to develop an efficient and accurate automatic system for sentiment analysis.
- Clique enumeration for large-scale networks
Maximal clique enumeration (MCE) is a long-standing problem in graph theory and has numerous important applications. Though extensively studied, most existing algorithms become impractical when the input graph is too large and is disk-resident. We first propose an efficient partition-based algorithm for MCE that addresses the problem of processing large graphs with limited memory. We then further reduce the high cost of CPU computation of MCE by a careful nested partition based on a cost model. Finally, we parallelize our algorithm to further reduce the overall running time.
