Good morning everyone! I've just finished reading Shyon Baumann's paper on "Intellectualization and Art World Development: Film in the United States." This excellent paper includes a substantial section of textual analysis where various film reviews are examined. These reviews are considered a fundamental space for the artistic legitimation of films, which, during the 1960s, increasingly gained artistic value. To achieve this, Baumann focuses on two dimensions: critical devices and lexical enrichment. The paper is a bit dated, and the methodologies used can be traced back to a time when text analysis tools were not as widespread or advanced. On the other hand, they are not as advanced yet. The question is: are you aware of literature/methodologies that could provide insights to extend Baumann's work using modern text analysis technologies?
In particular, following the dimensions analyzed by Baumann:
a) CHANGING LANGUAGE
- Techniques for the formation of artistic dictionaries that can replace the manual construction of dictionaries for artistic vocabulary (Baumann reviews a series of artistic writings and extracts terms, which are then searched in film reviews). Is it possible to do this automatically?
b) CHANGING CRITICAL DEVICES
Expanding methods in the direction of automation would allow observing changes in larger samples of textual sources, deepening our understanding of certain historical events. The data could go more in-depth, providing a significant advantage for those who want to view certain artistic phenomena in the context of collective action.
Thank you in advance!
Marco di Stasio
I appreciate you raising this insightful question on how to leverage modern text analysis methods to build on Baumann's foundational work examining artistic legitimation. Automated techniques can certainly help scale such textual analysis to larger corpora. However, care must be taken to ensure computational approaches do not lose the nuance of manual qualitative interpretation.
Regarding building artistic dictionaries, word embedding models like word2vec can help uncover semantic relationships and suggest terms related to a seed vocabulary. However, human validation is still important before applying these dictionaries to make inferences.
For sentiment analysis, deep learning approaches like BERT have shown promise, but domain-specific tuning and qualitative checks are key to account for the complex expressions in artistic reviews. Models pre-trained on social media may not transfer well.
To identify creators, named entity recognition using dictionaries, rules, and ML approaches can help. However disambiguation remains challenging, so human-in-the-loop verification is recommended before making claims about individuals.
Overall, I believe the best approach is applying computational methods as a starting point, but having experts qualitatively analyze a sample of results to catch subtleties these tools may miss. If used prudently and in collaboration with scholars like yourself, text mining can uncover exciting new insights at scale. Please feel free to reach out to discuss further.
Wishing you the very best,
#textanalysis #digitalhumanities #mixedmethods