The Entropy of Laughter: Discriminative Power of Laughter’s Entropy in the Diagnosis of Depression

Abstract

Abstract:Laughter is increasingly present in biomedical literature, both in analytical neurological aspects and in applied therapeutic fields. The present paper, bridging between the analytical and the applied, explores the potential of a relevant variable of laughter's acoustic signature-entropy-in the detection of a widespread mental disorder, depression, as well as in gauging the severity of its diagnostic. In laughter, the Shannon-Wiener entropy of the distribution of sound frequencies, which is one of the key features distinguishing its acoustic signal from the utterances of spoken language, has not been a specific focus of research yet, although the studies of human language and of animal communication have pointed out that entropy is a very important factor regarding the vocal/acoustic expression of emotions. As the experimental survey of laughter in depression herein undertaken shows, it was possible to discriminate between patients and controls with an 82.1% accuracy just by using laughter's entropy and by applying the decision tree procedure. These experimental results, discussed in the light of the current research on laughter, point to the relevance of entropy in the spontaneous bona fide extroversion of mental states toward other individuals, as the signal of laughter seems to imply. This is in line with recent theoretical approaches that rely on the optimization of a neuro-informational free energy (and associated entropy) as the main "stuff" of brain processing.

Plausibility of a Neural Network Classifier-Based Neuroprosthesis for Depression Detection via Laughter Records

“…It has also been argued that, in general, the increase of entropy in animal calls contributes to enhance their distinctiveness and attractiveness, improving the communication of emotional states between emitters and receivers (Takahashi et al, 2015). As we have already hinted (Navarro et al, 2016a), there might be a close interrelationship of sound entropies and neural entropies regarding the general “stuff” of brain processing (Friston, 2010; Carhart-Harris et al, 2014). Further up, the systemic repercussions of laughter, both physiological (respiratory, cardiovascular, immune, central nervous system, and autonomous nervous system, etc.)…”

“…The fine analysis of all the sound variables of laughter searching for systemic differences reflecting the underlying mental states becomes an interesting – and worthwhile – neurocomputational challenge. As the authors have already realized in previous works (Navarro et al, 2014, 2016a,b), statistical methods such as discriminant analysis and binary decision trees have been useful in the detection of systematic differences between depression patients and healthy controls in their responses to the same humorous stimuli.…”

“…Although laughter ordinarily is related to social interactions and to communication through the playful use of language, many other visual, tactile, physical, chemical, environmental influences, and physiological anomalies may elicit it: from tickling and physical play, to humorous – cartoons, to imitative laughter, “schadenfreude” occasions, neuropathological conditions, NO 2 and other anesthetic gasses, and so on (Poeck, 1985; Morreall, 1987; Provine, 2000; Ariniello, 2001; Martin, 2002; Weems, 2014). The social occurrence of laugher becomes preferentially related to a variety of bonding dynamics in between individuals (Marijuán and Navarro, 2011; del Moral et al, 2014; Navarro et al, 2016a,b). Thereafter, laughter appears in a wide variety of interpersonal relationships, very often triggered by linguistic exchanges, where it punctuates the meanings and behavioral implications and establishes a genuine emotional evaluation of the interrelationships.…”

“…Its structure may be described as follows (Urbain et al, 2013): firstly, it is composed of separate episodes (or “sentences”) that enclose some bouts (or “words”) which are themselves consisting of relatively large exhalation parts punctuated by brief inhalations, and the exhalation parts are in their turn containing a certain number of calls or plosives (pulses, or “syllables”). Numerous sound variables may be distinguished, among them (following Navarro et al, 2016a): the fundamental frequency F 0 of the plosives, the variations that this fundamental frequency presents in successive plosives, the irregular intervals that appear between plosives, the different vocalic sounds included (voiced versus unvoiced laughter), and very importantly the entropy, energy, and amplitude of the different frequencies that integrate the waveform. In the relationship between the sound structures of laughter and the linguistic utterances, it is very interesting that the entropy of the former appears to be higher than the entropy of the latter (Bea and Marijuán, 2003).…”

Attribute Selection Based on Constraint Gain and Depth Optimal for a Decision Tree

“…Decision trees are used extensively in data modelling of a system and rapid real-time prediction for real complex environments [ 1 , 2 , 3 , 4 , 5 ]. Given a dataset acquired by field sampling, a decision attribute is determined through a heuristic method [ 6 , 7 ] for training a decision tree.…”