The utility of the psycholexical approach for identifying military core values: Illustrated in a sample of Swiss career officers and NCOs

Values have always been a top priority in the military domains of leadership, training, ethical commitment, and psychological research. However, only a few studies have assessed value descriptors and their underlying dimensional structure in military organizations using an empirical psycholexical and factor analytical approach. This research project examined the structure of military values and derived core military values. Two studies were conducted in cooperation with the Swiss Armed Forces. In study 1, 25 military-specific value descriptors were identified based on a psycholexical analysis of military guidelines and in line with expert ratings by executive military leaders. In study 2, a questionnaire was filled out by a sample of 550 military professionals to capture their ratings of values as applied to everyday military decisions and actions. Principal component analysis in combination with Goldberg's top-down approach delivered five military value categories that reflect the military culture in Switzerland, characterized as (I) freedom, (II) social cohesion, (III) good soldiership, (IV) mutual respect, and (V) military conformity. Results are discussed in light of introducing a novel research approach to assessing the value structure and culture in military organizations.

Surfing the OCEAN: The machine learning psycholexical approach 2.0 to detect personality traits in texts

OBJECTIVE

We aimed to develop a machine learning model to infer OCEAN traits from text.

BACKGROUND

The psycholexical approach allows retrieving information about personality traits from human language. However, it has rarely been applied because of methodological and practical issues that current computational advancements could overcome.

METHOD

Classical taxonomies and a large Yelp corpus were leveraged to learn an embedding for each personality trait. These embeddings were used to train a feedforward neural network for predicting trait values. Their generalization performances have been evaluated through two external validation studies involving experts (N = 11) and laypeople (N = 100) in a discrimination task about the best markers of each trait and polarity.

RESULTS

Intrinsic validation of the model yielded excellent results, with R2 values greater than 0.78. The validation studies showed a high proportion of matches between participants' choices and model predictions, confirming its efficacy in identifying new terms related to the OCEAN traits. The best performance was observed for agreeableness and extraversion, especially for their positive polarities. The model was less efficient in identifying the negative polarity of openness and conscientiousness.

CONCLUSIONS

This innovative methodology can be considered a "psycholexical approach 2.0," contributing to research in personality and its practical applications in many fields.

The Impact of Our Personality on Others: The Lithuanian Comprehensive Lexical Taxonomy of Social Effects

Social effects represent the psychological (emotional, cognitive, and motivational) reactions evoked in other people by the expression of traits in behavior and emotion. From the transactional view on personality, studying the psycholexical structures of social effects can help to discover unique vs. common thought and behavior patterns, affects, and motivations, which are primarily related to personality dispositions. Thus, we developed the comprehensive taxonomy of social effects following the principles of the psycholexical approach. In the first study, two judges selected 9,625 person-descriptive terms—adjectives, type-nouns, attribute-nouns, and participles—from the Dictionary of the Standard Lithuanian Language. In the second study, six judges classified all the selected descriptors using German psycholexical methodology. Finally, a principal component analysis was performed, followed by varimax rotation for the 208 social-effect descriptors, separately for ipsatized self-ratings and observer-ratings from 203 to 204 Lithuanian students, respectively. We found out that the five-component solution was the best fit for self-ratings, whereas for observer-ratings it was a four-component structure. In this article, we present the results from the factor analyses and discuss our findings in the context of previous studies, as well as cross-language personality models.