Automated Content Analysis (ACA) refers to a collection of techniques used to automatically analyze media content. Because we often analyze textual data, it is also referred to with terms as Automated Text Analysis – however, there is no inherent reason why we could not include images or other media in our analysis. Research projects within the Digital Communication Methods Lab are currently working with Machine Vision for image analysis.

Given that more and more communication happens online and is available in a digital format, it makes sense to analyze this huge amount of data in an automated fashion. Situated in the framework of Computational Social Science, we use techniques from disciplines like computer science and computational linguistics, including dictionary- and word-frequency based methods, natural language processing, supervised and unsupervised machine learning, and start experimenting with deep learning.

Current research projects address topics such as:

  • How is media content replicated (e.g., the interplay between press releases, social media content, and news)?
  • How are groups represented in news (e.g., how much are groups linked to stereotypes?)?
  • What influences consumer reviews?
  • How are news article characteristics related to outcomes like news sharing or stock prices?
  • … and a lot more.

Methodologically, we try to create synergies where possible, meaning that we focus on writing reusable code in languages like Python and R, encourage code sharing on Github, and co-develop software like INCA, our own infrastructure for content analysis.

Selected Presentations and Publications:

An overview over different ACA techniques:

  • Boumans, J. W., & Trilling, D. (2016). Taking stock of the toolkit: An overview of relevant automated content analysis approaches and techniques for digital journalism scholars. Digital Journalism, 4(1), 8–23. doi:10.1080/21670811.2015.1096598

Specific studies:

  • Strycharz, J., Strauss, N., & Trilling, D. (2018). The role of media coverage in explaining stock market fluctuations:
    Insights for strategic financial communication. International Journal of Strategic Communication, 12(1), 67–85. http://doi.org/10.1080/1553118X.2017.1378220
  • Burggraaff, C., & Trilling, D. (2017). Through a different gate: An automated content analysis of how online news and print news differ. Journalism. doi:10.1177/1464884917716699
  • Jonkman, J.G.F., Trilling, D., Verhoeven, P., & Vliegenthart, R. (online first). More or less diverse: An assessment of the effect of attention to media salient company types on media agenda diversity in Dutch newspaper coverage between 2007 and 2013. Journalism, forthcoming. doi: 10.1177/1464884916680371
  • Kroon, A. C., & van der Meer, G. L. A. (in press). Who takes the lead? Investigating the reciprocal relationship between organizational and news agendas. Communication Research.
  • Van der Meer, G. L. A., Kroon, A. C., Verhoeven, P., & Jonkman, J. G. F. (2018). Mediatization and the disproportionate attention to negative news: The case of airplane crashes. Journalism Studies. doi:10.1080/1461670X.2018.1423632
  • Araujo, T.B., & Kollat, J. (in press). Communicating effectively about CSR on Twitter: The power of engaging strategies and storytelling elements. Internet Research