Experience

 
 
 
 
 
January 2018 – January 2019
Gothenburg

PostDoc

University of Gothenburg

I also hold a postdoc at the Centre for Digital Humanities. Here I get to experience research questions and methods needed for the Humanities.

Responsibilities include:

  • Text mining for the Digital Humanities
  • Epistomological issues related to Data Science for the Humanities
  • Teaching in the Digital Humanities Master programme
 
 
 
 
 
August 2014 – Present
Gothenburg

Researcher

University of Gothenburg

Field of research: automatic detection of language change using textual corpora. Sentiment mining (tools and dictionaries) for Swedish. Broadly, I am interested in information extraction from diachronic textual data, historical as well as modern. I have recently taken an interest in methodological issues of using data science for the digital humanities; how should the output of data science be evaluated and how should we go from the resutl of text mining to generating knowledge in the humanities?

Responsibilities include:

 
 
 
 
 
September 2013 – July 2014
Gothenburg

PostDoc

Chalmers University of Technology

Responsibilities include:

  • Computational models for language change detection
  • Multi-document Text Summarization
  • Organizing EACL2014

Selected Publications

Detecting word sense changes can be of great interest in the field of digital humanities. Thus far, most investigations and automatic methods have been developed and carried out on English text and most recent methods make use of word embeddings. This paper presents a study on using Word2Vec, a neural word embedding method, on a Swedish historical newspaper collection. Our study includes a set of 11 words and our focus is the quality and stability of the word vectors over time. We investigate if a word embedding method like Word2Vec can be effectively used on texts where the volume and quality is limited.
In DHN2018, 2018

We present a method for detecting word sense changes by utilizing automatically induced word senses. Our method works on the level of individual senses and allows a word to have e.g. one stable sense and then add a novel sense that later experiences change. Senses are grouped based on polysemy to find linguistic concepts and we can find broadening and narrowing as well as novel (polysemous and homonymic) senses. We evaluate on a testset, present recall and estimates of the time between expected and found change.
In RANLP 2017, 2017

Recent Publications

Human language constantly evolves due to the changing world and the need for easier forms of expression and communication. In this …

We created the first ever sense-disambiguated sentiment lexicon (SenSALDO) as an open source resource, freely available from …

We create a gold standard for sentiment annotation of Swedish terms, using the freely available SALDO lexicon and the Gigaword corpus.

Detecting word sense changes can be of great interest in the field of digital humanities. Thus far, most investigations and automatic …

In this paper we describe the creation of a gold standard for the sentiment annotation of Swedish terms as a first step towards the …

In this paper, we study the parameter tuning for both algorithms within the word sense disambiguation problem. The experiments are …

We present a method for detecting word sense changes by utilizing automatically induced word senses. Our method works on the level of …

Recent & Upcoming Talks

A Keynote for EDH2018 in Tartu.

Projects

*

Culturomics

Towards a Knowledge-based Culturomics.

Teaching

I have the following teaching experiences

2018

Supervisor, Master thesis, Spring
Lecturer, LV2190 Methods in Digital Humanities (part Methods for text mining and visualization), Spring

2017

Supervisor, Master thesis, Spring 2017
Lecturer, LT2304 Language Technology Resources, Autumn

2016

Supervisor, Master theses, Spring
Lecturer, LT2304 Language Technology Resources, Autumn

2011

Supervisor, Master thesis

2010

Supervisor, Master theses, 2010

2007

Matematisk statistik för K, (TMA072) 2007 formulas

Summer Course Mathematics (MVE800) 2007

Matematik TB (LMA162) 2007

Contact