Research On Visualization Of Literary Narration Based On Knowledge Graph

With the accelerated pace of life,it is difficult for people to spend a long time and energy reading literary works.In order to facilitate readers’ understanding of long literary works,clarify the plot and character relationships.This article proposes some methods that can quickly clarify the character relationships and plot development in long novels,assist readers in reading classic Chinese literature,save reading time,and also enrich the expression form of storylines by combining emotional elements with narrative visualization.This article mainly generates intuitive visual charts from two parts to assist readers in reading.1.In the first part,this paper takes the Rapids Trilogy as the research object,uses the common word analysis method to build a co-occurrence matrix and character relationship network,uses the Apriori algorithm to find strong association rules between characters,uses the LDA topic model to divide the article topics,uses knowledge acquisition methods to sort out and extract entities,attributes,and relationships in the text to establish a database,and uses the RDF data model to store the character relationship data,Build a knowledge graph.Finally,i Storyline is used to visualize the storyline of literary works and interact with the knowledge graph and storyline.This article combines knowledge graph and narrative visualization storyline,enabling readers to understand the relationship between characters while clarifying the plot of the story.2.In the second part,graph convolutional neural networks are introduced into the text sentiment classification of novels.Text-GCN is used to conduct sentiment analysis on Ba Jin’s novel "The Trilogy of the Rapids".i Storyline is used to visualize the storyline of literary works,and visual encoding adjustments are made based on the results of sentiment analysis in the generated storyline.The aggregation and dispersion of lines represent whether the characters appear in the same scene,The brighter the color of the lines,the more positive the emotions,making the visualization more vivid,full,and beautiful.The experimental results show that the accuracy of the Text-GCN model is superior to traditional sentiment classification methods on Chinese datasets.Enable readers to easily grasp the overall direction of the novel’s plot and have a clearer understanding of the emotional changes of the characters.Adding emotional elements can make the automatically generated storyline more vivid,full,and beautiful.This research adopts a series of methods to assist in reading the classic literary work "The Rapids Trilogy".By constructing a network of character relationships and visualizing the storyline,readers can quickly understand the character relationships while also clearly grasp the development of the story plot.In addition,emotional elements were incorporated into the narrative visualization storyline,showcasing the transformation of character emotions through color changes,enhancing the vividness of the storyline.This study has actively explored the visualization of narrative in literary works and can also be applied to other fields such as movies and drama scripts.