Re-presenting a Story by Emotional Factors using Sentiment Analysis Method

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