CIRHSS Deputy Secretary, Gede Primahadi Wijaya Rajeg, Ph.D., gave a guess talk at BIT School about the benefits of coding/computing skill and data science in Language Sciences. Gede presented three simple cases to illustrate the interaction of computational and data science skills using R for investigating language and texts.
- Generating a frequency list of words from hundreds of text files, followed by
- Extracting full-reduplication words
- Performing summary statistics for the length of the letters in the reduplication
- Visualising the results
- Extracting prominent/key terms in a collection of novels to reveal what those novels are about.
- Comparing collocates of one word (i.e. menolak ‘to refuse’) in two different text corpora.
Below are the recordings of the talk (in Indonesian). The first part is the presentation, while the second part is the Q&A section.