شناسايي حوزه‌هاي موضوعي داغ و روندها در رمان‌هاي علمي-تخيلي با استفاده از تكنيك‌هاي متن‌كاوي

Identification of Hot Topics an‎d Trends in Science Fiction based on Text Mining Techniques

علم اطلاعات و دانش شناسي

The objective of this study is to gain a better understan‎ding of the current hot topics an‎d important trends in science fiction literature. By utilizing text mining techniques, the study seeks to provide valuable insights into the subjects that interest readers of this genre. The statistical population for this research includes 353 Hugo Award-winning science fiction novels published from 1939 to the end of 2024. Book summaries were used for modeling an‎d analysis, an‎d after preprocessing the data, a combination of Latent Dirichlet Allocation (LDA) an‎d Term Frequency-Inverse Document Frequency (TF-IDF) was applied to identify the trending topics. To forecast future topics, a linear regression algorithm was employed, with the mean square error criterion used to eva‎luate the modelʹs accuracy. The findings revealed that the most frequent words in the texts include "person," "earth," "human," "time," "planet," an‎d "world." In terms of weighted frequency, "United States," "Artificial Intelligence," "New York," an‎d "Falling in Love" emerged as the words with the highest weight. Looking ahead, it is projected that upcoming novels will focus more on topics related to World War II, Artificial Intelligence, Thorne’s Justice, World War, Time Travel, Tau Ceti, an‎d Time Travelers. The topics “Nuclear Weapons in World War II” show a high correlation (0.96) with “On the Path of Terror” an‎d “Saving Humanity in the Far Distance.” Additionally, “Space Adventure” correlates strongly with topics such as “Genetic Engineering an‎d Destiny,” while “Saving Life an‎d Returning Home” an‎d “Saving Humanity in the Far Distance” have correlations of 0.96, 0.95, an‎d 0.94, respectively. A total of 12 clusters were identified, with the main key topics as follows: 1) “Genetic Engineering an‎d Destiny,” 2) “Artificial Intelligence an‎d Time Travel,” 3) “Advanced Technology an‎d Space Exploration,” 4) “The United States in World War II,” 5) “Adventure in Space,” 6) “Journey to the Unknown World,” 7) “On the Path of Assassination,” 8) “Saving Life an‎d Returning Home,” 9) “Nuclear Weapons in World War II,” 10) “Future Life Form,” 11) “Saving Humanity in the Far East,” an‎d 12) “Confronting Alien Races an‎d Nuclear Weapons.” Ultimately, “Genetic Engineering an‎d Destiny” an‎d “Artificial Intelligence an‎d Time Travel” were identified as the hot topics of interest.

5

122449