Natural Language Processing

Dream content during lucid dreams and out-of-body experiences, differences and similarities

We conducted interviews with subjects who experienced LD and subjects who had OBEs frequently. A portion of them kept a dream journal for two months with precise instructions on how to write down their dreams. The collected dreams were analyzed by automatic methods of analysis of emotions such as EmoLex and Sentisense, also with classifiers such as Empath. The dream stories provided by the participants were scored with a series of ratings using a method based on Hall and Van de Castle’s dream content scoring system upon which we developed variations and additional measures to adapt to the requirements of our task.

Structural differences between non-lucid, lucid dreams and out-of-body experience reports assessed by graph analysis

In this work we analyse dream reports that include non-lucid, lucid dreams and out-of-body experiences initiated from sleep paralysis.

DebtHunter: A Machine Learning-based Approach for Detecting Self-Admitted Technical Debt

This paper presents DebtHunter, a natural language processing (NLP)- and machine learning (ML)- based approach for identifying and classifying SATD in source code comments. The proposed classification approach combines two classification phases for differentiating between the multiple debt types.