This final virtual workshop introduces participants to topic modeling, an exciting realm of text analysis. The workshop focuses on two key methodologies: topic modeling and keyword-assisted topic models(keyATM). Participants will gain a practical understanding of topic modeling, a powerful unsupervised technique that extracts hidden themes and patterns from text collections. They'll learn how to apply topic modeling to identify dominant topics within textual data and how to interpret the results.

In this second Text Analysis Virtual Workshop event series, we will cover data preprocessing, which is a set of steps and techniques applied to raw text data before analysis. These steps include tokenization, lowercasing, stop word removal, stemming and lemmatization, removing special characters and further text cleaning. The goal of data preprocessing is to transform and prepare the text data for further analysis, ensuring that the data is accurate, consistent and suitable for extracting meaningful insights.

In this first of three Text Analysis Virtual Workshop events, we delve into foundational understanding and practical applications of text analysis. Defining concepts like text mining and natural language processing, we explore their uses in social sciences, digital humanities and beyond. We will then discover how these methods address complex inquiries, enriching our grasp of societal phenomena. Beyond academia, we will showcase text analysis's efficacy in marketing, finance and more. Join us in uncovering its transformative potential and versatile impact across disciplines.

In collaboration with the Virginia G. Piper Center for Creative Writing, the Labriola Center will be co-hosting a book talk with Ramona Emerson, author of Shutter. This book talk will take place on the second floor of Hayden Library in the Labriola Center from 12 p.m. to 2 p.m. Dr. Jerome Clark (Diné), Assistant Professor, School of Humanities, Arts and Cultural Studies will lead the panel.

Join the ASU Library’s Researcher Support team for an informal conversation about the Year of Open Science! 2023 has been designated by the White House and federal funding agencies as the year to promote policies, practices and resources to catalyze a shift to open. We’ll talk about the U.S. Office of Science and Technology's definition of open science and their current activities, followed by an open conversation about resources and tools that are available or needed to help shift the research culture at ASU.

This virtual workshop aims to unveil the diverse applications of machine learning techniques in domains such as social sciences, digital humanities and beyond. We will start with a quick overview of p-value statistical significance test approach and then move to demonstrate huge potential of machine learning algorithms to provide us with important predictions and advance social science and digital humanities research as an alternative to the p-value approach.

In the follow-up Visualization 2 virtual workshop, we will venture into ggplot's advanced features, equipping participants with visualization techniques to resolve complex challenges. We will first explore how to create informative animated visualizations. Attendees will then have the opportunity to uncover the power of coordinates and maps, illuminating how data can be spatially represented for deeper insights. We will explore various maps and geospatial data using the Leaflet package.

Visualization 1 serves as an insightful introduction to the power of ggplot. The virtual workshop will guide participants through the art of crafting compelling visualizations that convey complex insights and stories. We will start by explaining why we should care about visualizations. By understanding the "why" behind visualization, we can gain an appreciation for its pivotal role in modern data analysis. The workshop will then dive into the core concepts of visual relationships between variables, unraveling the diverse forms of visual illustrations.

Subscribe to ASU Library