Two Voices, Two Worlds Lexical Signatures and Discursive Architectures in Le sel de tous les oublis and Nulle autre voix
Résumé
This article proposes a computer-assisted literary analysis of two major novels in contemporary Algerian literature: : Le sel de tous les oublisby Yasmina Khadra and Nulle autre voix by Maïssa Bey. Starting from the hypothesis that these two works, while sharing a post-traumatic context, embody two radically opposed narrative paradigms – social wandering and intimate confession – we mobilize textual analysis tools to quantify and visualize this structural divergence.
The methodology relies on a triangulation of tools from digital humanities: Orange Data Mining for visual lexical exploration, and Voyant Tools for analyzing contexts and syntagms. Data analysis reveals a centrifugal lexical structure in Khadra, organized around space, displacement, and social confrontation, while Bey’s lexicon is centripetal, focused on writing, memory, and the body as a site of trauma. Topic modeling (HDP) confirms this dichotomy by identifying distinct semantic constellations for each work.
By objectifying these lexical signatures, our study demonstrates how textual data analysis enriches critical hermeneutics, offering a reproducible and transparent method. Themes were evaluated according to their internal coherence and inter-run stability, validating the robustness of the results. This contribution combines scientific rigor and literary sensitivity, illustrating how digital humanities can serve contemporary Algerian criticism.
Références
BEY, M. (2018). Nulle autre voix. Éditions Barzakh.
BLEI, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet allocation. Journal of Machine Learning Research, 3, 993–1022.
CARUTH, C. (Ed.). (1995). Trauma: Explorations in memory. Johns Hopkins University Press.
CHATMAN, S. (1978). Story and discourse: Narrative structure in fiction and film. Cornell University Press.
FELMAN, S., & LAUB, D. (1992). Testimony: Crises of witnessing in literature, psychoanalysis, and history. Routledge.
GENETTE, G. (1972). Figures III. Éditions du Seuil.
— (1980). Narrative discourse: An essay in method (J. E. LEWIN, Trad.). Cornell University Press.
Griffiths, T. L., & Steyvers, M. (2004). Finding scientific topics. Proceedings of the National Academy of Sciences, 101(Suppl. 1), 5228–5235.
JOCKERS, M. L. (2013). Macroanalysis: Digital methods and literary history. University of Illinois Press.
KHADRA, Y. (2020). Le sel de tous les oublis. Éditions Julliard.
LEBART, L., & SALEM, A. (1994). Statistique textuelle. Dunod.
MAINGUENEAU, D. (2014). Discours et analyse du discours. Armand Colin.
McENERY, T., & H3ardie, A. (2012). Corpus linguistics: Method, theory and practice. Cambridge University Press.
MIMNO, D., WALLACH, H. M., TALLEY, E., LEENDERS, M., & McCALLUM, A. (2011). Optimizing semantic coherence in topic models. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (pp. 262–272).
MORETTI, F. (2005). Graphs, maps, trees: Abstract models for literary history. Verso.
NEWMAN, D., LAU, J. H., GRIESER, K., & BALDWIN, T. (2010). Automatic evaluation of topic coherence. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the ACL (pp. 100–108).
ORANGE TEAM. (2020). Orange: A component-based data mining framework. https://orange.readthedocs.io
RICOEUR, P. (1983). Temps et récit. 1. L’intrigue et le récit historique. Éditions du Seuil.
ROCKWELL, G., & Sinclair, S. (2016). Hermeneutica: Computer-assisted interpretation in the humanities. MIT Press.
SAID, E. W. (1978). Orientalism. Pantheon Books.
SINCLAIR, S., & ROCKWELL, G. (2012). Voyant Tools: Rethinking close reading with machine reading. In Proceedings of the Digital Humanities 2012 Conference. University of Hamburg.
SINCLAIR, S., & ROCKWELL, G. (2016). Voyant Tools: Seeing your data [software]. https://voyant-tools.org
TEH, Y. W., JORDAN, M. I., BEAL, M. J., & BLEI, D. M. (2006). Hierarchical Dirichlet processes. Journal of the American Statistical Association, 101(476), 1566–1581.
UNDERWOOD, T. (2015). Why literary data matters: A rejoinder to commentators. Journal of Cultural Analytics, 1, 1–21.
