Revealing semantic and emotional structure of suicide notes with cognitive network science

Abstract

Understanding how people who commit suicide perceive their cognitive states and emotions represents an important 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 ideas and emotional states of people who committed suicide through an analysis of emotional balance motivated by structural balance theory, semantic prominence and emotional profiling. Our results indicate that connections between positively- and negatively-valenced terms give rise to a degree of balance that is significantly higher than in a null model where the affective structure is randomized and in a linguistic baseline model capturing mind-wandering in absence of suicidal ideation. We show that suicide notes are affectively compartmentalized such that positive concepts tend to cluster together and dominate the overall network structure. Notably, this positive clustering diverges from perceptions of self, which are found to be dominated by negative, sad conceptual associations in analyses based on subject-verb-object relationships and emotional profiling. A key positive concept is “love”, which integrates information relating the self to others and is semantically prominent across suicide notes. The emotions constituting the semantic frame of “love” 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.

Emotional profiling and cognitive networks unravel how mainstream and alternative press framed AstraZeneca, Pfizer and COVID-19 vaccination campaigns

“…The authors identified a strong polarisation in favour and against humanitarian interventions to immigration mainly correlated with political factions, in agreement with previous social network approaches 34 . Teixeira and colleagues 49 used semantic/syntactic networks to reconstruct stances expressed in suicide notes and found negative perceptions of concepts like “love”, distorted by suicide ideation when compared to control data. Mokryn and colleagues found that the emotional words expressed in movie reviews were predictive of the emotions inspired by those movies, further strengthening a connection between textual data and cognitive/emotional content.…”

“…Through the lens of cognitive network science 12 , 16 , 40 , discourse content, centrality and frames can all be measured via interpretable network metrics and, importantly, visualised. These aspects provide experimenters direct access into the structure of stances expressed in texts 45 and also in the psychology of text authors 46 , 49 . A key advantage of TFMNs is their ability to unveil semantic frames surrounding specific concepts in discourse as network neighbourhoods of concept associations.…”

Contextual Graph Attention Network for Aspect-Level Sentiment Classification

“…Moreover, to detect sentiment and emotions around aspects "gender" and "gap" in 10,000 tweets, Stella [16] used a multi-layer perceptron to extract syntactic structure information and build a network of non-stopwords. Similarly, to investigate sentiments and emotions around aspects "love" and "live" in suicide notes, Sofia [17] used syntactic structure information to construct subject-verb-object triads.…”

Disentangling the Climate Divide with Emotional Patterns: a Network-Based Mindset Reconstruction Approach

“…Communication materials like texts are an open view to the mindset of the authors, which is a proxy for the structure of language and its associations in the human mind (Teixeira et al, 2021).…”