Online Invited Seminar Talk
Revealing Semantic and Emotional Structure of Suicide Notes with Cognitive Network Science
Laboratory of Digital and Computational Demography
Online Invited Seminar Talk, May 18, 2021
Sofia Teixeira from Hospital da Luz Learning Health, Luz Saúde, Lisbon (Portugal) introduced a network representation of suicidal ideation expressed in multiple suicide notes.
Understanding how people who commit suicide perceive their cognitive states and emotions represents a crucially open scientific challenge. We build upon cognitive network science, psycholinguistics, and semantic frame theory to introduce a network representation of suicidal ideation as expressed in multiple suicide notes. By reconstructing the knowledge structure of such notes, we reveal interconnections between the semantic ideas and emotional states of people who committed suicide through structural balance theory, semantic prominence, and emotional profiling.
Our results show that suicide notes have a higher degree of balance than one would expect in a linguistic baseline model capturing mind-wandering in absence of suicidal ideation. This is reflected in a positive clustering where positively perceived concepts are prominently central and are found to cluster together, reducing contrast with more peripheral and negative concepts.
Combining semantic frames with emotional data, we find that a key positive concept is “love” and that the emotions populating its semantic frame combine joy and trust with anticipation and sadness, which can be linked to psychological theories of meaning-making as well as narrative psychology. Our results open new ways for understanding the structure of genuine suicide notes and may be used to inform future research on suicide prevention.
Sofia Teixeira holds a PhD in Information Systems and Computer Engineering from Universidade de Lisboa (Portugal). Currently, she works as a research scientist at Hospital da Luz Learning Health in Lisbon. Previously, she was a postdoc at the Indiana University Network Science Institute and a junior researcher at the Instituto de Engenharia de Sistemas e Computadores - INESC-ID (at the Information & Decision Support Systems group).
Sofia's research interests include modelling and analyzing complex systems through the development of new algorithms on graphs and the application of network science and machine learning methods. Her fields of interest, among others, are Human Behavior, Computational Social Sciences, Network Medicine, Cognitive Science, Network Neuroscience, and Computational Epidemiology.