What a word count cannot read: the emotional ARC of crime and punishment measured with the labMT dictionary and a reader's interpretation

Abstract

Computer methods that measure the emotional arc of a novel by averaging the happiness of its words are now widely used. This study applies one such method, the labMT word list, to the English translation of Dostoevsky's Crime and Punishment by Constance Garnett, chapter by chapter, and compares the result with the author's own reading of the novel. The author reads the novel as the shape "fall", with guilt gradually consuming Raskolnikov, and the epilogue as light. The word count disagrees on both points at the level of chapters: the six parts of the novel stay within a narrow band (5.63-5.72), the epilogue is the darkest part (5.48), and no simple story shape fits well (the best correlation is 0.30). A closer reading changes the picture in part. Of three epilogue sentences the author chose as the lightest after seeing the chapter results, two score among the brightest in the novel (higher than 99% and 88% of its sentences), while the third scores among the darkest tenth; the mood of the last chapter rises from 5.11 in its first fifth to 5.80 in its last; and the words that carry her reading in the English translation, "renewed", "renewal" and "regeneration", are not in the dictionary at all. The low score of the epilogue comes mostly from negations and from words of its prison and illness setting, while its ending scores as light, as the reader saw.

Keywords: sentiment analysis, emotional arc, labMT, Dostoevsky, Crime and Punishment, digital humanities

Әдебиеттер тізімі

1. Reagan A.J., Mitchell L., Kiley D., Danforth C.M., Dodds P.S. The emotional arcs of stories are dominated by six basic shapes // EPJ Data Science. 2016. Vol. 5. Art. 31. https://doi.org/10.1140/epjds/s13688-016-0093-1
2. Dodds P.S., Harris K.D., Kloumann I.M., Bliss C.A., Danforth C.M. Temporal patterns of happiness and information in a global social network: hedonometrics and Twitter // PLoS ONE. 2011. Vol. 6, No. 12. e26752. https://doi.org/10.1371/journal.pone.0026752 (labMT 1.0 word list: https://hedonometer.org, accessed 29.10.2026).
3. Dostoevsky F. Crime and Punishment / translated by C. Garnett. Project Gutenberg eBook #2554. https://www.gutenberg.org/ebooks/2554 (accessed 29.10.2026).

Дәйексөз келтіру үлгісі

Sapayeva Danaiya What a word count cannot read: the emotional ARC of crime and punishment measured with the labMT dictionary and a reader's interpretation // Central Asian Scientific Journal. – 2026. – No. 4(32), Vol. 2. – Pp. 301–304.