| layout | title | nav_order | has_toc | has_children |
|---|---|---|---|---|
home |
Home |
1 |
false |
false |
Exploring Themes with Topic Modeling belongs to a series of workshops on computational text analysis.
When working with texts at scale, we may wish to generalize the "about-ness" of the entire corpus without having to read through each document. Computational methods can allow us to quickly explore relationships between frequently used words and make inferences about themes from the results returned.
Topic modeling is a natural language processing technique that groups words in “topics” based on the frequency of their appearance near each other in a text. It can be used to interpret thematic trends within a large body of text.
In this workshop, we will introduce topic modeling using three different computational tools.
- Basic computer literacy (creating and working with different file types, navigating interfaces, using shortcut keys and so on)
- If you are newer to Python programming, the Identifying Proper Nouns with Named Entity Recognition module introduces using Python for text analysis in Anaconda and so, may be helpful to complete first
By the end of the workshop, you will be able to:
- Define topic modeling
- Use at least one tool to perform topic modeling on a text corpus
- Explain the limitations of topic modeling
Going through the workshop from start to finish (and you need not necessarily!) will take you approximately 1 hour to complete, depending on your familiarity with Python and whether you are working with your own dataset alongside the sample corpus.
McMaster University is situated in Ohròn:wakon which is the traditional territories of the Erie, Neutral, Huron-Wendat, Haudenosaunee and Mississaugas. This land is covered by the “Dish With One Spoon Wampum Belt Covenant”, an agreement between the Haudenosaunee confederacy and Anishinaabe nations to ensure those who live here take only what they need, leave enough in the dish for others, and keep the dish clean. This land is also covered by the Between the Lakes Treaty of 1792 and is very close to the 1784 Haldimand Treaty, which holds the land six miles to each side of the Grand River as a tract for Six Nations, which is currently not being honored.
Many of us at the Sherman Centre took the First Nations' Information Governance Centre's OCAP course this past year which stands for Ownership, Control, Access, and Possession. We encourage you to learn more about OCAP and Indigenous data management practices more broadly, including the OCAS principles endorsed by the Manitoba Métis Federation, the principles of Inuit Qaujimajatuqangit, ᐃᓄᐃᑦ ᑕᐱᕇᑦ ᑲᓇᑕᒥ (Inuit Tapiriit Kanatami) National Inuit Strategy on Research, and Global Indigenous Data Alliance’s CARE principles.