遠讀是一種用於文學研究的計算方法，是利用自動化的演算法去擷取並分析文學作品中的資訊，本研究開發出一種利用分群演算法、可視化方法、以及語言分析的工具去遠讀一本小說的處理方法，來獲得小說的情節與角色間的相互關係，以本研究為例，小說<魔戒>中的角色網絡就是利用此方法來處理的，小說人物的資訊是利用一種叫做專有名詞辨識的方法擷取出來的，接著利用一種叫做最小展開聚類的演算法去分析確切的角色網絡，並建構出社群的網絡結構。
接著進行統計分析調查角色的作用還有信息流，整體角色網絡結構的可視化是利用一個叫做Gephi的軟體，藉由網絡的可視化更進一步展示出角色之間的關係，而主要角色的個性特徵則是利用一個叫做語文探索與字詞計算的分析工具去分析角色的對話內容，此外，為了瞭解小說的發展，上述的聚類與統計分析是和故事線一併進行的，最後，本研究利用了語文探索與字詞計算的工具去調查了小說的情感基調隨著小說隨故事線的演進。

Distant reading is a computational approach in literary studies that applies automated algorithms to extract and analyze literary information. In this work, I developed an approach for the distant reading of a novel by combining clustering algorithms, visualization methods, and language analytic tools to obtain a perspective of its plot and visualize the interaction between characters. As an example, the character network in “The Lord of the Rings” was analyzed with this approach. The information of characters in the novel was extracted by named entity recognition (NER). The identified character network was then analyzed by the minimum span clustering (MSC) algorithm to construct the community structure of the network. Statistical analyses were performed to investigate the role of characters as well as the flow of information. The overall structure of the character network was visualized by the software Gephi to further reveal the relationship between characters. The personality traits of the main characters were analyzed from their dialogues using the linguistic and word count (LIWC) analyzer. Furthermore, to obtain a comprehension of the novel’s development, the above clustering and statistical analyses were carried out along with the storyline. Finally, I used LIWC to investigate the emotional tone of the novel plot as the story progresses.

Ardanuy, M. C. and C. Sporleder (2015). "Clustering of novels represented as social networks." Linguistic Issues in Language Technology 12(4).

Chang, Y. F. and C. M. Chen (2011). "Classification and Visualization of the Social Science Network by the Minimum Span Clustering Method." Journal of the American Society for Information Science and Technology 62(12): 2404-2413.

Chang, Y. F. and C. M. Chen (2014). "Visualizing the clustering of financial networks and profitability of stocks." Journal of Complex Networks 3(2): 303-318.

Chen, R.H.-G and Chen, C.-C and Chen, C.-M (2019). "Unsupervised cluster analyses of character networks in fiction:
Community structure and centrality." Knowledge-Based Systems: 11.

Curry I. (2009)“A Hybrid AI Approach to the Classification of Emotive Text” International Conference on Artificial Intelligence (as part of WORLDCOMP'09)

Hu, G.-M., et al. (2015). "Clustering and visualizing similarity networks of membrane proteins." Proteins: Structure, Function, and Bioinformatics 83(8): 1450-1461.

James, W. P. and Martha, E. F. (1999) “Linguistic Inquiry and Word Count (LIWC)”

Semi, M. and Juyong, P. (2019). "Modeling narrative structure and dynamics with networks, sentiment analysis, and topic modeling." 20.