The main contribution of this Master's thesis is a novel way of doing text comparison using word vector representations (word2vec) and dimensionality reduction (t-SNE). This yields a bird’s-eye view of different text sources, including text summaries and their source material, and enables users to explore a text source like a geographical map.
This talk introduces computational social science as a new research discipline, gives a brief introduction to natural language processing and explains how word vector representations are computed and how to use them in Python. Word vector representations like word2vec encode semantic relationships like gender and "is the capital city of". This makes it easy to find similar words and compare them visually. To illustrate this, I am using the gensim and scikit-learn Python libraries to compare my own Google searches from 2011 and 2014 (PyCon Sweden) and Wikipedia article revisions (PyData London).
My talk at the Stockholm Natural Language Processing Meetup. I explained how word2vec is implemented and how to use it in Python with gensim. When words are represented as points in space, the spatial distance between words describes a similarity between these words. In this talk, I explore how to use this in practice and how to visualize the results (using t-SNE)
Download 'word2vec - From theory to practice'
My Bachelor thesis yields feedback on advantages, disadvantages, usability problems and suggested improvements of a non-mimicking digital musical interface with an integrated music composition aid.
For this thesis, a non-mimicking musical interface with an integrated music composition aid was designed, implemented and evaluated. The music composition aid is based on templates derived from an analysis of a set of pop songs regarding their chord progressing in terms of functional theory. The interface and the music composition aid were evaluated in a Thinking-aloud study with six users and analysed with a qualitative approach according to Mayring.
This presentation explains how to incorporate contextual information into recommender systems and provides an overview on the state of the art in context-aware recommendation systems. It was our final presentation for the "Special Course in Computer and Information Science - User Modelling & Recommender Systems" at Aalto University. Together with Eirini Kolomvrezou.
Download the presentation on 'Context-aware recommendation systems'
This paper explores the intersection of Human Computer Interaction (HCI) and Artificial Intelligence (AI) and identifies opportunities for future collaboration. Based on a literature review, the historic relationship of the fields, their theoretical foundations and possible applications are discussed. Written as part of the HCI Research Seminar at KTH Royal Institute of Technology.
Download 'On The Intersection Of Human-Computer Interaction (HCI) And Artificial Intelligence (AI)'
This is a paper presentation on massive-scale automated analysis of news-content and research methods in the age of digital journalism. It connects this to computational social science and digital humanities. It was presented as part of the "Special Course in Language Technology" at Aalto University.