Julian Kohne

Scientific Advisor / PhD Student

What I do

As a scientific advisor at GESIS, I am coordinating our efforts to establish new services for social scientists to collect, process, analyze, and get access to digital behavioral data. The term refers to all traces of human behavior that are created or can be made accessible through the use of digital technologies. This includes for example data from social media, webtracking, smartphones, contact sensors or other smart devices. In combination with high quality survey data, these types of data allow us to study the digitization of society, new digital phenomena, and established social science questions from new perspectives!

As a PhD student at Ulm University, I am part of the molecular psychology lab and investigate how interpersonal relationships can be quantified using chat logs, specifically donated WhatsApp chat logs. I am developing interactive methods for transparent, ethical and secure data donation, and investigate how social relationships are expressed through different communication patterns.

Download my Curriculum Vitae.

Interests

Computational Social Science
Interpersonal Relationships
Data Science
Text as Data
Group Dynamics
Social Networks

Education

PhD in Psychology, in progress
Ulm University
M.Sc in Social & Organizational Psychology, 2016
University of Groningen
B.Sc in Psychology, 2014
University of Groningen

My Research

and other projects

Call me sexist, but...: Revisiting Sexism Detection Using Psychological Scales and Adversarial Samples.

In this paper, we outline the different dimensions of sexism by grounding them in their implementation in psychological scales. From the scales, we derive a codebook for sexism in social media which we use to annotate existing and novel datasets. Next, we leverage the annotated datasets to generate adversarial examples, and test the reliability of sexism detection methods.

Mattia Samory, Indira Sen, Julian Kohne, Fabian Flöck, Claudia Wagner

Call me sexist, but...: Revisiting Sexism Detection Using Psychological Scales and Adversarial Samples.

The Role of Network Structure and Initial Group Norm Distributions in Norm Conflict

In this chapter, we present an agent-based model that simulates the adoption of norms in two interacting groups. We explore this phenomenon while varying relative group sizes and homophily/heterophily (two features of network structure), and initial group norm distributions.

Julian Kohne, Nathalie Gallagher, Zeynep Melis Kirgis, Rocco Paolillo, Lars Padmos, Fariba Karimi

The Role of Network Structure and Initial Group Norm Distributions in Norm Conflict

Skills

Social Psychology

Expert

Statistics

Advanced

Shiny

Advanced

Machine Learning

Enthusiast

Git

Enthusiast

Experience

and previous positions

PhD Student

Ulm University

Sep 2020 – Present Cologne

In my PhD project, I am investigating how interpersonal relationships can be quantified using chat logs, specifically donated WhatsApp chat logs. I am developing interactive methods for transparent, ethical and secure data donation, and investigate how social relationships are expressed through different communication patterns. The project is conducted in collaboration with the Stanford Social Media Lab

Scientific Advisor for Digial Behavioral Data

GESIS

Oct 2017 – Present Cologne

Coordination of our institute wide efforts to expand the GESIS service portfolio to digital behavioral data, conceptualization of new services and acquisition of third-party funding. The position includes a component for research in data and web science.

Computational Social Science Internship

GESIS

Apr 2017 – Jul 2017 Cologne

Analysis of text and metadata on token-level on a dataset of 1.3 million Wikipedia revisions. The goal was to quantify the learning curves of editors.

Scientific Traineeship

Enexis Netbeheer / University of Groningen

Oct 2015 – Oct 2016 Groningen

Evaluation of the „Buurkracht“ project by Enexis, a quantitative long-term study of a bottom-up energy conservation initiative.

Research Assistant

University of Groningen

Oct 2014 – Jun 2015 Groningen

Questionnaire design and maintenance in Qualtrics, statistical analyses in R and SPSS

Certificates

and professional development

Project Manager (IHK)

IHK Cologne May 26, 2021 – June 30, 2021

Workshop Contents:

Project management according to DIN 69901
Types of project organization
Cost and resource management
Working with specification sheets
Time management

See certificate

Big Data - Introduction to Data Science with Python

GESIS September 16, 2019 – September 18, 2019

Workshop Contents:

The Python Data Science Stack
Data Exploration and Preprocessing
Web Data Acquisition
Data visualization
Machine Learning

LaTeX

GESIS November 22, 2018 – November 23, 2018

Workshop Contents:

Scientific Papers in LaTeX
Bibliographies
Tables
Equations
LaTeX with R and Stata
LaTeX for posters and presentations

Practical Introduction to Text Mining

GESIS April 18, 2018 – April 19, 2018

Workshop Contents:

Computer-assisted text coding
Metadata evaluation
Linguistic preprocessing
Lexicometrics
Topic Models
Methodological Integration

An Introduction to R Markdown

GESIS April 15, 2018 – April 15, 2018

Workshop Contents:

Introduction to R Markdown
Writing scienctific papers in R Markdown
Citations in R Markdown

The Data Scientists Toolbox

Coursera January 5, 2017 – December 1, 2017

In this course you will get an introduction to the main tools and ideas in the data scientist’s toolbox. The course gives an overview of the data, questions, and tools that data analysts and data scientists work with. There are two components to this course. The first is a conceptual introduction to the ideas behind turning data into actionable knowledge. The second is a practical introduction to the tools that will be used in the program like version control, markdown, git, GitHub, R, and RStudio.

See certificate

Machine Learning

Coursera December 12, 2016 – January 5, 2017

This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. Topics include: (i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks). (ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning). (iii) Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI). The course will also draw from numerous case studies and applications, so that you’ll also learn how to apply learning algorithms to building smart robots (perception, control), text understanding (web search, anti-spam), computer vision, medical informatics, audio, database mining, and other areas.

See certificate

Contact

Tweets by JuuuuKoooo

julian.kohne[at]gesis.org
+49 (0221) 47694-222
Tweet me