Over the past decade, there has been an explosion of interest in network analysis research across the social sciencesand computer science. As it is an idea that can be applied in many fields, this study, in particular, its influence in the literature.We present a method for extracting social networks from literature. This study focuses on the relation between novel itself,narration in fiction and was carried out experiments with 89 undergraduate students. They were instructed to write down theirremembered memory of the novel after reading the novel ‘Chronicle of a death foretold.’ We extract features from the socialnetworks of characters in students’ recall story and examine their differentiation with one another, as well as novel’s setting.This study compares graph theory–based cohesion measures characters’ relationship in novel and students’ story. Our resultssuggest an alternative explanation for difference in social networks.

Remembering events is affected by personal emotional status. We examined the psychological status, personalfactors, and social factor of undergraduate students (N=64) and got summaries of a story, Chronicle of a Death Foretold fromthem. As transfer learning, we collected 38,265 movie review data to train a sentimental analysis model based on convolutionalneural network, using the model to score each summary. The results of CES-D and PANAS show the relationship betweenemotion and memory retrieval; depressed people have shown a tendency of representing a story more negatively, and seemedless expressive. People with full of emotion have retrieved their memory more expressively, using more negative words. Thecontributions of this study can be summarized as follows: First, we lighten the relationship between emotion and its effects onstoring or retrieving memories. Second, we suggest objective methods to evaluate the intensity of emotion in words, using asentimental analysis model.