Kurs: SS23: Data Science for Digital Humanities 2

Abschnittsübersicht

Abschnitt General auswählen

General

Alles einklappen Alles aufklappen
- Aktivität Language of the CourseThe lectures will be partial... auswählen
  
  Language of the Course
  The lectures will be partially in English and German.
  The material will be in English.
  Questions (in person and the Forum) can be asked in both languages.
  Proof of performance
  During the Course: Active participation, weekly assignments and project presentations.
  Final examination:
  To be announced.
  
  Schedule and location
  The sessions will take place Thursdays 10-12 c.t. in the Sensalight Technologies building (John-Skilton-Str. 8a), in room 4.23 (seminar room on the 4th floor).
  Additional information
  Since each session contains hands-on parts, students are required to bring their laptops.
  A working Python Stack (easiest to set up using Anaconda) has to be installed on your machines.
  If Anaconda is not yet installed on your machine, please install it before our first meeting so that we can solve eventual problems quickly together in the first lecture.
  Please also make sure to connect your machine to the university's official Wi-Fi (eduroam) since Bayern-WLAN is remarkably unreliable at times.
- Aktivität Announcements auswählen
  
  Announcements Forum
- Aktivität Questions and Discussions auswählen
  
  Questions and Discussions Forum
- Aktivität Zoom: Screenshare auswählen
  
  Zoom: Screenshare Zoom Meeting
Abschnitt Content (planned) auswählen

Content (planned)
27.4. Session #1: Introduction
Recap of DS4DH1
Course organization

4.5. Session #2: Recap of DSDH1
Pandas
Numpy, Scipy
Seaborn

11.5. Session #3: Corpus linguistics
Lexical association measures
Multi-word expressions, collocations, idioms
Lexico-semantic resources: WordNet, BabelNet, PanLex

22.5. Session #3: Topic modeling -- exceptionally on Monday, 14-16
Latent Dirichlet Allocation
Practical examples with LDA in Gensim
Homework project #1: pick a corpus, induce topics, analyze topics and topical distribution of documents, prepare a small-scale presentation

25.5. Session #4: Networks
Introduction to Graph Theory
Node importance -- degree centrality, closeness centrality, betweeness centrality
Shortest paths
Practical exercises with networkx
Homework project #2: analysis of a large-scale network dataset; prepare a small-scale presentation with insights

1.6. Session #5: Evaluation & Statistical Testing
Common evaluation measures for classification and regression
Gold-standard annotation and inter-annotator agreement
Significance testing (parametric: Student’s t-test; non-parametric: Wilcoxon’s test

15.6. Session #6: Student presentations -- Topic Modeling Homeworks
22.6. Session #7: Student presentations -- Network Analysis Homeworks
29.6. Session #8: Deep Learning
Convolutional NNs
Recurrent NNs
Attention mechanism and Transformers
Practical exercises in keras

6.7. Session #9: Interpretability & Fairness
Explainability and interpretability of machine learning models
Biases and fairness: data bias, model bias

13.7. Session #10: Guest Lecture
A talk by a prominent researcher in the area of Computational Humanities
Abschnitt Recap: Material from DS4HUM-1 auswählen

Recap: Material from DS4HUM-1
- Aktivität Notebook: Python-Basics (HTML-Version) auswählen
  
  Notebook: Python-Basics (HTML-Version) Datei
- Aktivität Notebook: Python-Basics 2 (HTML-Version) auswählen
  
  Notebook: Python-Basics 2 (HTML-Version) Datei
- Aktivität Notebook: Numpy (HTML-Version) auswählen
  
  Notebook: Numpy (HTML-Version) Datei
- Aktivität Notebook: Acquisition and Preprocessing (HTML-Version) auswählen
  
  Notebook: Acquisition and Preprocessing (HTML-Version) Datei
- Aktivität Notebook: Descriptive Statistics (HTML-Version) auswählen
  
  Notebook: Descriptive Statistics (HTML-Version) Datei
- Aktivität Notebook: Deep-dive into Seaborn (HTML-Version) auswählen
  
  Notebook: Deep-dive into Seaborn (HTML-Version) Datei
- Aktivität Notebook: Classification (.ipynb) auswählen
  
  Notebook: Classification (.ipynb) Datei
- Aktivität Slides: Text Classification and Clustering auswählen
  
  Slides: Text Classification and Clustering Datei
- Aktivität Notebook: Text processing (.ipynb) auswählen
  
  Notebook: Text processing (.ipynb) Datei
- Aktivität Slides: Lexical semantics auswählen
  
  Slides: Lexical semantics Datei
- Aktivität Slides: Text representations auswählen
  
  Slides: Text representations Datei
- Aktivität Slides: Information Extraction auswählen
  
  Slides: Information Extraction Datei
Abschnitt Session 1: Introduction auswählen

Session 1: Introduction
- Aktivität Jupyter Notebooks from DS4DH1 (HTML) auswählen
  
  Jupyter Notebooks from DS4DH1 (HTML) Datei
- Aktivität L1: Course introduction auswählen
  
  L1: Course introduction Datei
Abschnitt Session 1.5: Recap auswählen

Session 1.5: Recap
- Aktivität Notebook: Numpy & Pandas (HTML-Version) auswählen
  
  Notebook: Numpy & Pandas (HTML-Version) Datei
- Aktivität Notebook: Seaborn (HTML-Version) auswählen
  
  Notebook: Seaborn (HTML-Version) Datei
Abschnitt Session 2: Corpus linguistics & lexicon-semantic resources auswählen

Session 2: Corpus linguistics & lexicon-semantic resources
- Aktivität Notebook: Corpus Linguistics (HTML-Version) auswählen
  
  Notebook: Corpus Linguistics (HTML-Version) Datei
Abschnitt Session 3: Topic Modeling auswählen

Session 3: Topic Modeling
- Aktivität TM: Slides auswählen
  
  TM: Slides Datei
- Aktivität TM: Notebook (ipynb) auswählen
  
  TM: Notebook (ipynb) Datei
- Aktivität TM: Notebook (HTML) auswählen
  
  TM: Notebook (HTML) Datei
Abschnitt Session 4: Networks auswählen

Session 4: Networks
- Aktivität Notebook: Graphs & Network analysis (HTML-Version) auswählen
  
  Notebook: Graphs & Network analysis (HTML-Version) Datei
Abschnitt Session 5: Evaluation & Statistical Testing auswählen

Session 5: Evaluation & Statistical Testing
- Aktivität Note: Evaluation & Significance Testing (HTML-Version) auswählen
  
  Note: Evaluation & Significance Testing (HTML-Version) Datei
Abschnitt Session 6: Student presentations of topic modeling auswählen

Session 6: Student presentations of topic modeling
Abschnitt Session 7: Student presentations on graph analysis auswählen

Session 7: Student presentations on graph analysis
Abschnitt Session 8: Deep Learning auswählen

Session 8: Deep Learning
- Aktivität Intro2ML (from DS4DH1) auswählen
  
  Intro2ML (from DS4DH1) Datei
- Aktivität Intro2DL: Autoencoders, CNNs, RNNs auswählen
  
  Intro2DL: Autoencoders, CNNs, RNNs Datei
- Aktivität Notebook: Deep Learning (HTML) auswählen
  
  Notebook: Deep Learning (HTML) Datei
- Aktivität Notebook: Deep Learning (ipynb) auswählen
  
  Notebook: Deep Learning (ipynb) Datei
Abschnitt Session 9: Interpretability & Fairness auswählen

Session 9: Interpretability & Fairness
- Aktivität Notebook: Explainability & Fairness (HTML) auswählen
  
  Notebook: Explainability & Fairness (HTML) Datei
- Aktivität Notebook: Interpretability & Fairness (ipynb) auswählen
  
  Notebook: Interpretability & Fairness (ipynb) Datei
Abschnitt Final Project auswählen

Final Project
- Aktivität Submission deadline: 31.9.23Please use the provide... auswählen
  
  Submission deadline: 31.9.23
  Please use the provided template for styling your project report.
  Project reports can be either written in German or English.
- Aktivität Project data auswählen
  
  Project data Link/URL
- Aktivität Final Project: Description auswählen
  
  Final Project: Description Datei
- Aktivität Project report: LaTex Template auswählen
  
  Project report: LaTex Template Datei
- Aktivität Project report: Word template auswählen
  
  Project report: Word template Datei
- Aktivität Project report: Overleaf LaTex template auswählen
  
  Project report: Overleaf LaTex template Link/URL

Abschnittsübersicht

Language of the Course

Proof of performance

Schedule and location

Additional information