Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Aug 18;12(8):292.
doi: 10.3390/bs12080292.

Only Words Count; the Rest Is Mere Chattering: A Cross-Disciplinary Approach to the Verbal Expression of Emotional Experience

Daniela Laricchiuta  1 , Andrea Termine  1 , Carlo Fabrizio  1 , Noemi Passarello  1   2 , Francesca Greco  3 , Fabrizio Piras  1 , Eleonora Picerni  1 , Debora Cutuli  1   4 , Andrea Marini  5 , Laura Mandolesi  2 , Gianfranco Spalletta  1 , Laura Petrosini  1
Affiliations

Only Words Count; the Rest Is Mere Chattering: A Cross-Disciplinary Approach to the Verbal Expression of Emotional Experience

Daniela Laricchiuta et al. Behav Sci (Basel). .

Abstract

The analysis of sequences of words and prosody, meter, and rhythm provided in an interview addressing the capacity to identify and describe emotions represents a powerful tool to reveal emotional processing. The ability to express and identify emotions was analyzed by means of the Toronto Structured Interview for Alexithymia (TSIA), and TSIA transcripts were analyzed by Natural Language Processing to shed light on verbal features. The brain correlates of the capacity to translate emotional experience into words were determined through cortical thickness measures. A machine learning methodology proved that individuals with deficits in identifying and describing emotions (n = 7) produced language distortions, frequently used the present tense of auxiliary verbs, and few possessive determiners, as well as scarcely connected the speech, in comparison to individuals without deficits (n = 7). Interestingly, they showed high cortical thickness at left temporal pole and low at isthmus of the right cingulate cortex. Overall, we identified the neuro-linguistic pattern of the expression of emotional experience.

Keywords: Natural Language Processing; alexithymia; cortical thickness; emotional processing; machine learning.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Verbal analysis of Toronto Structured Interview for Alexithymia (TSIA) transcripts. In the Natural Language Processing (NLP), the Linguistic Profiling Analysis showed High Alexithymia subjects produced more pseudowords or non-words (tag: Other) (A1), used the present tense of auxiliary verbs more (A2), used the possessive determiners less (A3), used fewer coordinating conjunctions (A4), and less coordinating conjunction relation (A5), when compared to Low Alexithymia subjects. In the boxplot are reported the percentages of frequency (median ± percentile). ** P adjusted = 0.01; * at least P adjusted = 0.03. Semantic analysis showed that High Alexithymia subjects used less emotional keywords (feel, happy, to express) and more filler words (maybe, in conclusion, huh) (B). This pattern of differential use of words is confirmed by unsupervised Latent Semantic Analysis (LSA), showing cluster separation between High, Medium (participants with middle alexithymia levels), and Low Alexithymia subjects on a two-dimensional space representing the latent semantic structure. The orthogonal dimensions represent semantically related cluster of words, and Low and High Alexithymia subjects are divided by Dimension 4 and 5 in the LSA space (C). Unsupervised Latent Dirichlet Allocation (LDA) identified 20 topics, described by the top five words for frequency of use. Three topics were significantly different between High and Low Alexithymia subjects (P ≤ 0.05; Topic 1: fashion, reason, end, minute, effect; Topic 2: day, home, week, sister, vacation; Topic 3: sense, parent, news, scene, patient) (D). Exploring sentiment polarization, High Alexithymia subjects were characterized by a reduced frequency of emotion-related words, when compared to Low Alexithymia subjects, specifically for anger and disgust (* at least P = 0.025) (E). In the histograms are reported the frequency mean (mean ± standard deviation).
Figure 2
Figure 2
Machine Learning Analysis on Cross-Disciplinary Data. Natural Language Processing (NLP) data were aggregated with demographic, neuroimaging, and psychological data to predict Toronto Structured Interview for Alexithymia (TSIA) scores. Candidate features (n = 92) were extracted using univariate filtering with Spearman correlation method, Principal Components Regression (PCR) model with three components was selected as it had the best performance over evaluation metrics assessed in Leave-One-Out Cross-Validation (LOOCV) (R2 = 0.86; Root Mean Square Error—RMSE = 0.35) (A,B). Variable importance is reported (C1,C2). Namely, 85 candidate features resulted to belong to NLP, 3 to psychological measures, 2 to neuroimaging data, and 2 to demographic data. The variable importance of neuroimaging data showed that the increased left temporal pole thickness (orange colored area, D1) predicted increased TSIA scores, while increased right isthmus cingulate thickness (orange colored area, D2) predicted decreased TSIA scores. In (D1,D2) left is left.
Figure 3
Figure 3
Machine Learning Analysis on Speech Records. Univariate correlation filtering was applied to select 212 candidate acoustic features belonging to the ComParE feature set and Principal Components Regression (PCR) model with 5 components was selected as the best fitting based on R2 and Root Mean Square Error (RMSE) metrics in Leave-One-Out Cross-Validation (LOOCV) (R2 = 0.74; RMSE = 6.74) (A,B). Relative variable importance was computed over the domains of ComParE low-level descriptors, namely sound quality, spectral, cepstral, and prosodic (C). Representative differences in audio tracks (recorded in responding to an item of Difficulty in Describing Feelings—DDF) from High Alexithymia subjects and Low Alexithymia subjects can be observed in spectrograms (D1,D2).
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

  • The Cerebellum as an Embodying Machine.
    Petrosini L, Picerni E, Termine A, Fabrizio C, Laricchiuta D, Cutuli D. Petrosini L, et al. Neuroscientist. 2024 Apr;30(2):229-246. doi: 10.1177/10738584221120187. Epub 2022 Sep 2. Neuroscientist. 2024. PMID: 36052895 Free PMC article. Review.

References

    1. Lindquist K.A. Language and Emotion: Introduction to the Special Issue. Affect. Sci. 2021;2:91–98. doi: 10.1007/s42761-021-00049-7. - DOI - PMC - PubMed
    1. Sauter D.A. Is There a Role for Language in Emotion Perception? Emot. Rev. 2018;10:111–115. doi: 10.1177/1754073917693924. - DOI
    1. Bucci W. Discourse patterns in “good” and troubled hours: A multiple code interpretation. J. Am. Psychoanal. Assoc. 1997;45:155–187. doi: 10.1177/00030651970450010301. - DOI - PubMed
    1. Bucci W. Overview of the Referential Process: The Operation of Language Within and Between People. J. Psycholinguist. Res. 2021;50:3–15. doi: 10.1007/s10936-021-09759-2. - DOI - PubMed
    1. LeDoux J.E. What emotions might be like in other animals. Curr. Biol. 2021;31:R824–R829. doi: 10.1016/j.cub.2021.05.005. - DOI - PubMed

LinkOut - more resources