Automatic Extraction of Social Networks from Literary Text: A Case Study on Alice in Wonderland

In this paper we present results for two tasks: social event detection and social network extraction from a literary text, Alice in Wonderland. For the first task, our system trained on a news corpus using tree kernels and support vector machines beats the baseline systems by a statistically significant margin. Using this system we extract a social network from Alice in Wonderland. We show that while we achieve an F-measure of about 61% on social event detection, our extracted unweighted network is not statistically distinguishable from the un-weighted gold network according to popularly used network measures.