Hostname: page-component-848d4c4894-jbqgn Total loading time: 0 Render date: 2024-06-25T12:55:14.503Z Has data issue: false hasContentIssue false

L'analyse automatisée du ton médiatique : construction et utilisation de la version française du Lexicoder Sentiment Dictionary

Published online by Cambridge University Press:  13 July 2016

Dominic Duval*
Département de science politique, Université Laval
François Pétry*
Département de science politique, Université Laval
Centre d'analyse des politiques publiques, Université Laval, Pavillon Charles-De Koninck 1030, avenue des Sciences-Humaines, Université Laval, Québec (Québec) G1 V 0A6, Email:
Département de science politique, Université Laval, Pavillon Charles-De Koninck 1030, avenue des Sciences-Humaines, Université Laval, Québec (Québec) G1 V 0A6, Email:


This article introduces a new dictionary for the automated analysis of the tone of French media. We named it the French Lexicoder Sentiment Dictionary (LSDFr) in reference to the English lexicon developed by Young and Soroka (2012), the Lexicoder Sentiment Dictionary (LSD), from which the LSDFr was built. We compare the LSDFr to the only other French sentiment lexicon, Linguistic Inquiry and Word Count (LIWC). First, we detail the construction of the dictionary. We then test the internal validity of the LSDFr comparing it with a corpus of manually coded texts. Finally, we test the external validity of LSDFr by measuring how the media tone, calculated using our dictionary, predicts voting intentions in the last four Quebec elections. Our goal is to enable other researchers to conduct media analyses with a comparable corpus of texts in French.


Cet article introduit un nouveau dictionnaire permettant l'analyse automatisée du ton des médias francophones, que nous avons appelé Lexicoder Sentiment Dictionnaire Français (LSDFr) en référence au lexique anglophone de Young et Soroka (2012), Lexicoder Sentiment Dictionary (LSD) à partir duquel le LSDFr a été construit. Une fois construit, nous comparons le LSDFr au seul autre dictionnaire francophone existant de ce genre, Linguistic Inquiry and Word Count (LIWC). Nous testons ensuite la validité interne du LSDFr en le comparant avec un corpus de textes codés manuellement. Nous testons enfin la validité externe du LSDFr en mesurant jusqu'où le ton médiatique, calculé à l'aide de notre dictionnaire, prédit les intentions de vote des Québécois lors des quatre dernières campagnes électorales. En développant cet outil, notre objectif est de permettre à d'autres chercheurs d'effectuer des analyses médiatiques dans un corpus de textes comparables en français.

Research Article
Copyright © Canadian Political Science Association (l'Association canadienne de science politique) and/et la Société québécoise de science politique 2016 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)



Andreevskaia, Alina et Bergler, Sabine. 2006. « Mining WordNet for fuzzy sentiment: Sentiment tag extraction from WordNet glosses ». Communication présentée à la 11ème Conference of the European Chapter of the Association for Computational Linguistics, Trento, Italy.Google Scholar
Ansolabehre., Stephen et Iyengar, Shanto. 1995. Going Native: How Attack Adds Shrink and Polarize the Electorate. New York: Free Press.Google Scholar
Ansolabehre, Stephen, Iyengar, Shanto et Simon, Adam. 1999. « Replicating experiments using aggregate and survey data: the case of negative advertising and turnout ». American Political Science Review 93 (4): 901909.CrossRefGoogle Scholar
Ansolabehre, Stephen, Iyengar, Shanto, Simon, Adam et Valentino, Nicholas. 1994. « Does attack advertizing demobilize the electorate? ». The American Political Science Review 88 (4): 829838.Google Scholar
Baumeister, Roy F., Bratslavsky, Ellen, Finkenauer, Catrin et Vohs, Kathleen D.. 2001. « Bad is stronger than good ». Review of General Psychology 5(4): 323370 Google Scholar
Benoit, Kenneth. 2015. Quanteda: Quantitative Analysis of Textual Data. <> (consulté le 20 octobre 2015).+(consulté+le+20+octobre+2015).>Google Scholar
Blei, David M., Ng, Andrew Y. et Jordan, Micheal I.. 2003. « Latent Dirichlet Allocation ». Journal of Machine Learning Research 3: 9931022.Google Scholar
Bouchet-Valat, Milan. 2014. SnowballC: Snowball stemmers based on the C libstemmer UTF-8 library.Google Scholar
Bradley, Margaret M. et Lang, Peter J.. 1999. Affective Norms for English Words (ANEW): Stimuli, instruction manual and affective ratings. Gainesville: Center for Research in Psychophysiology, University of Florida.Google Scholar
Buckley, Chris, Singhal, Amit, Mitra, Mandar et Salton, Gerald. 1995. « New retrieval approaches using SMART ». Proceedings of the Fourth Text Retrieval Conference (TREC-4): 2548.Google Scholar
Chateauraynaud, Francis, Reber, Bernard et Van Meter, Karl. 2003. « Marlowe, Prospero et la technologie littéraire ». Bulletin de Méthodologie Sociologique 79 : 546.Google Scholar
Cho, Jaeho, Boyle, Micheal P., Keum, Heejo, Shevy, Mark D., McLeod, Douglas M., Shan, Dhavan V. et Pan, Zhongdang. 2003. « Media, terrorism, and emotionality: Emotional differences in media content and public reactions to the September 11th terrorist attacks ». Journal of Broadcasting & Electronic Media 47: 309327.CrossRefGoogle Scholar
Cibois, Philippe. 1995. « Tri-deux version 2.2 ». Bulletin de Méthodologie Sociologique 46 : 119124.Google Scholar
Daku, Mark. 2015. Newspaper Coverage of Employee Leave Policies in the United States (1980–2014). Communication présentée à la conférence internationale sur les politiques publiques. Milan, Italie.Google Scholar
Daku, Mark et Dionne, Kim Y.. 2015. The ISIS of Biological Agents: How Domestic Media Coverage of Ebola Can Overshadow International Response. Communication présentée à la conférence internationale sur les politiques publiques. Milan, Italie.Google Scholar
Dolamic, Lijiljana et Savoy, Jacques. 2010. « When stopword lists make the difference ». Journal of the American Society for Information Science and Technology 61(1) : 200203.Google Scholar
Edelman, Murray. 1985. « Political language and political reality ». Political Science and Politics 18: 1019.Google Scholar
Eshbaugh-Soha, Matthew. 2010. « The tone of local presidential news coverage ». Political Communication 27 : 121140.CrossRefGoogle Scholar
Farnsworth, Stephen J. et Lichter, Samuel R.. 2010. The nightly news nightmare: Media coverage of U.S. presidential elections, 1988–2008. Lanham, MD: Rowman & Littlefield.Google Scholar
Fournier, Patrick, Cutler, Fred, Soroka, Stuart, Stolle, Dietlind et Bélanger, Éric. 2013. « Riding the Orange Wave: Leadership, Values, Issues, and the 2011 Canadian Election ». Revue canadienne de science politique 46 (4): 135.Google Scholar
Gélineau, François et Blais, André. 2015. « Comparing measures of campaign negativity : Expert judgments, manifestos, debates and advertisements ». Dans New Perspectives on Negative Campaigning: Why Attack Politics Matters, dir. Nai, Allesandro et Walter, Anne-Marie S.. Colchester: ECPR Press Studies in European Political Science.Google Scholar
Gentzkow, Matthew et Shapiro, Jesse M.. 2010. « What drives media slant? Evidence from U.S. daily newspapers ». Econometrica 78: 3571.Google Scholar
Giasson, Thierry, Brin, Colette et Sauvageau, Marie-Michèle. 2010. « La couverture médiatique des accommodements raisonnables dans la presse écrite québécoise: Vérification de l'hypothèse du tsunami médiatique ». Canadian Journal of Communication 35 : 431453.Google Scholar
Hart, Rod P. 2000. DICTION 5.0: The text analysis program. Thousand Oaks, CA: Sage-Scolari.Google Scholar
Hart, Rod P. 2001. « Redeveloping diction: Theoretical considerations ». Dans Theory, method, and practice in computer content analysis, dir. West, Mark D.. Westport, CT: Ablex.Google Scholar
Hopmann, David N., Vliegenthart, Rens, de Vreese, Claes et Albaek, Erik. 2010. « Effects of Election News Coverage: How Visibility and Tone Influence Party Choice ». Political Communication 27 (4): 389407.Google Scholar
Lau, Richard R. 1982. « Negativity in political perceptions ». Political Behavior 4 (4): 353377.Google Scholar
Lowry, Dennis T. 2008. « Network TV news framing of good vs. bad economic news under Democrat and Republican presidents: A lexical analysis of political bias ». Journalism & Mass Communication Quarterly 85: 483498.Google Scholar
Lucas, Christopher, Nielsen, Richard, Roberts, Margaret E., Stewart, Brandon M., Storer, Alex et Tingley, Dustin. 2015. « Computer assisted text analysis for comparative politics ». Political Analysis 23 (2): 254277.Google Scholar
McComas, Katherine et Shanahan, James. 1999. « Telling stories about global climate change: Measuring the impact of narratives on issue cycles ». Communication Research 26: 3057.Google Scholar
McDermott, Monika. L. et Frankovic, Kathleen A.. 2003. « Horserace polling and the survey method effects: an analysis of the 2000 campaign ». Public Opinion Quarterly 67 (2) : 244264.Google Scholar
Marcus, George E., Neuman, W. Russel et MacKuen, Micheal. 2000. Affective intelligence and political judgment. Chicago: University of Chicago Press.Google Scholar
Martindale, Colin. 1975. Romantic progression: The psychology of literary history. Washington, DC: Hemisphere.Google Scholar
Martindale, Colin. 1990. The clockwork muse: The predictability of artistic change. New York, NY: Basic Books.Google Scholar
Miller, Patrick R. 2011. « The emotional citizen: emotion as a function of political sophistication ». Political Psychology 32 (4): 575600.Google Scholar
Murthy, Dhiraj et Petto, Laura R.. 2014. « Comparing Print Coverage and Tweets in Elections A Case Study of the 2011–2012 U.S. Republican Primaries ». Social Science Computer Review 33 (3): 298314.Google Scholar
Nadeau, Richard, Niemi, Richard, Fan, David et Amato, Timothy. 1999. « Elite economic forecasts, economic news, mass economic judgments, and presidential approval ». Journal of Politics 61: 109135.Google Scholar
Ottati, Victor C., Steenbergen, Marco R. et Riggle, Ellen. 1992. « The cognitive and affective components of political attitudes: Measuring the determinants of candidate evaluations ». Political Behavior 14: 423442.Google Scholar
Pennebaker, James W., Francis, Martha et Booth, Roger J.. 2001. Linguistic Inquiry and Word Count: LIWC 2001. Mahwah, NJ: Erlbaum.Google Scholar
Piolat, Annie, Booth, Roger J., Chung, Cindy K., Davids, Morgana et Pennebaker, James W.. 2011. « La version française du dictionnaire pour le LIWC: modalités de construction et exemples d'utilisation ». Psychologie française 56 (3): 145159.CrossRefGoogle Scholar
Porter, Martin F. 1980. « An algorithm for suffix stripping ». Program 14 (3): 130137.CrossRefGoogle Scholar
Reinert, Max. 1987. « Classification descendante hiérarchique et analyse lexicale par contexte : Application au corpus des poésies d'Arthur Rimbaud ». Bulletin de Méthodologie Sociologique 13 : 5390.Google Scholar
Rozin, Paul et Royzman, Edward B.. 2001. « Negativity bias, negativity dominance, and contagion ». Personality and Social Psychology Review 5 (4): 296320.Google Scholar
Ruedin, Didier. 2013. « The Role of Language in the Automatic Coding of Political Texts ». Swiss Political Science Review 19 (4): 539545.Google Scholar
Salton, Gerard et Buckley, Chris. 1997. « Improving retrieval performance by relevance feedback ». Readings in information retrieval 24 (5): 355363.Google Scholar
Savoy, Jacques. 1999. « A stemming procedure and stopword list for general French corpora ». Journal of the Association for Information Science and Technology 50 (10): 944952.Google Scholar
Soroka, Stuart. 2006. « Good news and bad news: Asymmetric responses to economic information ». The Journal of Politics 68 : 372385.Google Scholar
Soroka, Stuart. 2012. « The Gatekeeping Function: Distributions of Information in media and the real World ». The Journal of Politics 74 (2): 514528.CrossRefGoogle Scholar
Soroka, Stuart. 2014. Negativity in Democratic Politics: Causes and Consequences. New York: Cambridge University Press.CrossRefGoogle Scholar
Soroka, Stuart, Bodet, Marc André, Young, Lori et Andrew, Blake. 2009. « Campaign news and vote intentions ». Journal of Elections, Public Opinion and Parties 19: 359376.Google Scholar
Soroka, Stuart et McAdams, Stephen. 2015. « News, Politics, and Negativity ». Political Communication 32: 121.Google Scholar
Soroka, Stuart, Young, Lori and Balmas, Meital. 2015. « Bad News or Mad News? Sentiment Scoring of Negativity, Fear, and Anger in News Content ». AAPSS 659 (1): 108121.Google Scholar
Stewart, Brandon et Grimmer, Justin. 2013. « Text as Data: The Promise and Pitfalls of Automatic Content Analysis Methods for Political Texts ». Political Analysis 21 (3): 267297.Google Scholar
Stone, Philip J., Dumphy, Dexter C., Smith, Marshall S. et Ogilvie, Daniel M.. 1966. The General Inquirer: A computer approach to content analysis. Cambridge, MA: MIT Press.Google Scholar
Strapparava, Carlo et Valitutti, Allessandro. 2004. WordNet-Affect: An affective extension of WordNet. Communication préparée pour la quatrième conférence internationale sur Langage Resources and Evaluation. Lisbonne, Portugal.Google Scholar
Subasic, Pero et Huettner, Alison. 2001. « Affect analysis of text using fuzzy typing ». IEEE Transactions on Fuzzy Systems 9: 483496.Google Scholar
Tourangeau, Roger et Galešić, Mirta. 2008. « Conceptions of Attitudes and Opinions ». Dans The Sage Handbook of Public Opinion Research, dir. Donsbach, Wolfgang et Traugott, Michael W.. Los Angeles : Sage Publications.Google Scholar
Van Meter, Karl, Cibois, Philippe et de Saint Léger, Mathilde. 2004. « Correspondence and Co-Word Analysis of Ten Years of BMS Articles 1993–2003 ». Bulletin de Méthodologie Sociologique 81: 4857.Google Scholar
Whissell, Cynthia. 1989. « The dictionary of affect in language ». Dans Emotion: Theory and research, dir. Plutchik, Robert et Kellerman, Henry. New York, NY: Harcourt Brace.Google Scholar
Young, Lori et Soroka, Stuart. 2012. « Affective News: The Automated Coding of Sentiment in Political Texts ». Political Communication 29: 205231.Google Scholar