Title : Modeling the dynamics of mood and depression
| Presenter | Fiemke Both |
| Abstract | Both for developing human-like virtual agents and for developing intelligent systems that make use of knowledge about the emotional state of the user, it is important to model the mood of a person. In my talk, I will present a model for simulating the dynamics of mood in human or human-like agents. Psychological theories about a uni-polar clinical depression were used as a basis for inspiration and validation. A formal mathematical model is introduced that integrates several aspects of these existing theories. The model was analyzed both by simulations as mathematically, and it was shown that the model can describe how stress factors under some conditions can lead to a depression, while it won’t lead to a depression under other conditions. |
Title : Good News or Bad News? Conducting sentiment analysis on Dutch text to dinstinguish between positive and negative relations
| Presenter | Wouter van Atteveldt |
| Abstract | Many research questions in political communication can be answered by representing text as a network of positive or negative relations between actors and issues such as conducted by Semantic Network Analysis. This paper presents a system for automatically determining the polarity (positivity/negativity) of these relations by using techniques from Sentiment Analysis. We used a Machine Learning model trained on the manually annotated news coverage of the Dutch 2006 elections, collecting lexical, syntactic, and word-similarity based features, and using the syntactic analysis to focus on the relevant part of the sentence. The performance of the full system is significantly better than the baseline with an F1 Score of 0.63. Additionally, we replicate four studies from an earlier analysis of these elections, attaining correlations of >0.8 in three out of four cases. This shows that the presented system can be immediately used for a number of analyses. |