Data Analytics for Discourse Analysis with Python

Dennis Tay is Professor at the Department of English and Communication, the Hong Kong Polytechnic University. He is Co-Editor-in-Chief of Metaphor and the Social World, Associate Editor of Metaphor and Symbol, Academic Editor of PLOS One, and Review Editor of Cognitive Linguistic Studies. His recent Routledge publication is Time Series Analysis of Discourse: Method and Case Studies (2020).

• Introduction Defining data analyticsData analytics for discourse analysisThe case of psychotherapy talkOutline of the bookQuantifying language and implementing data analyticsQuantification of language: word embeddingQuantification of language: LIWC scoresIntroduction to Python and basic operationsChapter 2 Monte Carlo simulationsIntroduction to MCS: bombs, birthdays, and casinosThe birthday problemSpinning the casino rouletteCase study: Simulating missing or incomplete transcriptsStep 1: Data and LIWC scoringStep 2: Simulation runs with a train-test approachStep 3: Analysis and validation of aggregated outcomesPython code used in this chapterChapter 3 Cluster analysisIntroduction to cluster analysis: creating groups for objectsAgglomerative hierarchical clustering (AHC)k-means clusteringCase study: Measuring linguistic (a)synchrony between therapists and clientsStep 1: Data and LIWC scoringStep 2: k-means clustering and model validationStep 3: Qualitative analysis in contextPython code used in this chapterChapter 4 ClassificationIntroduction to classification: predicting groups from objectsCase study: Predicting therapy types from therapist-client language Step 1: Data and LIWC scoringStep 2: k-NN and model validationPython code used in this chapterChapter 5 Time series analysisIntroduction to time series analysis: squeezing juice from sugarcaneStructure and components of time series dataTime series models as structural signaturesCase study: Modeling and forecasting psychotherapy language across sessions Step 1: Inspect seriesStep 2: Compute (P)ACFStep 3: Identify candidate modelsStep 4: Fit model and estimate parametersStep 5: Evaluate predictive accuracy, model fit, and residual diagnosticsStep 6: Interpret models in contextPython code used in this chapterConclusionData analytics as a rifle and a spadeApplications in other discourse contextsCombining data analytic techniques in a projectFinal words: invigorate, collaborate, and empower