Search Results (41)

The deployment of small language models (SLMs) at the edge raises a fundamental behavioral question: under a fixed word budget, how do these models prioritize semantic content? This paper investigates content selection in two representative edge SLMs—gemma3n-e4b and Llama-3.2-3B—under systematic word-budget compression when generating person descriptions in English and Thai. A 2 × 2 (model × language) factorial design yielded 9360 observations across 18 profiles, 13 budget levels (1–25 words, odd-step intervals), and 10 trials per cell. Output richness was quantified via an Information Density Score (IDS), a binary annotation-based metric capturing seven attributes: name, occupation, gender, education, income, and two personality traits. Results confirm strong, generally increasing IDS–budget relationships across all conditions (Pearson r = 0.663–0.903). In English, gemma3n-e4b reached every key threshold exactly four words ahead of Llama-3.2-3B (B50: w = 7 vs. 11; B70: w = 13 vs. 17; B80: w = 17 vs. 21). In Thai, both models converged at B50 (w = 9), but gemma retained a four-word lead at B70 (w = 13 vs. 17), while Llama never reached B80 (max IDS = 0.796 at w = 25). Occupation was the invariant anchor across all conditions (retention ≥ 0.969). Models diverged on secondary attributes: gemma suppressed Gender (4.8% English, 24.2% Thai), while Llama deprioritized Education (23.6% English, 15.2% Thai; 0.267 at w = 25 in Thai). In Thai, gemma’s personality traits overtook Income in the salience hierarchy—a reordering absent in English. Gemma showed 2.5–3.8× higher within-trial consistency than Llama in both languages. These findings indicate that content selection under budget pressure is determined primarily by model architecture rather than linguistic context, and that Thai reduces but does not eliminate the cross-architecture compression efficiency gap. Full article

Linguistic accommodation during human–AI interaction has been measured in only one direction at a time, leaving the relative magnitude of each side and the trajectory of within-conversation change unresolved. A symmetric within-versus-between conversation dissociation design applied to 1319 multi-turn English GPT-4o conversations from WildChat measures both user-side and model-side function word adaptation within the same data, revealing two distinct temporal dynamics. The model’s adaptation is front-loaded, with strong initial accommodation at the first turn followed by stabilization, while users converge gradually across subsequent turns on interpersonal pronoun dimensions with no progressive change in topic-related categories. In 500 Switchboard human–human conversations, per-conversation similarity slopes are significantly negative ($p=0.022$), though the multilevel interaction is marginal ($p=0.055$). Because the pronoun dimensions on which users converge are the primary linguistic markers through which personality traits manifest in natural language use, this progressive convergence may represent a linguistic indicator of shifts in communicative self-presentation during extended human–AI conversation. Full article

Recommendation systems are popular information systems that help consumers manage information overload. Whilst personality has been recognised as an important factor influencing consumers’ choice, it has not yet been fully exploited in recommendation systems. This study proposes a restaurant recommendation approach that integrates customer personality traits, opinions and preferences, extracted either directly from online review platforms or derived from electronic word of mouth (eWOM) text using information extraction techniques. The proposed method leverages the concept of venue personality grounded in personality–brand congruence theory, which posits that customers are more satisfied with brands whose personalities align with their own. A novel model is introduced that combines fine-tuned BERT embeddings with linguistic features to infer users’ personality traits from the text of their reviews. Customers’ preferences are identified using a custom named-entity recogniser, while their opinions are extracted through structural topic modelling. The overall framework integrates neural collaborative filtering (NCF) features with both directly observed and derived information from eWOM to train an extreme gradient boosting (XGBoost) regression model. The proposed approach is compared to baseline collaborative filtering methods and state-of-the-art neural network techniques commonly used in industry. Results across multiple performance metrics demonstrate that incorporating personality, preferences and opinions significantly improves recommendation performance. Full article

The ability of large language models to recall human emotions provides a novel opportunity to investigate links among memory, affect, and mental health. This study explores whether the Emotional Recall Task (ERT), a free word-association paradigm, can reveal cognitive markers of distress in both humans and large language models (LLMs). Using spreading activation simulations grounded in cognitive network science, we examined how the recall of emotional concepts (e.g., stress, anxiety, and depression) relates to psychometric measures of well-being and personality. In Study 1, correlations were tested between activation dynamics and clinical scales (DASS-21, PANAS, and Life Satisfaction) in human participants (N = 1200) and artificial participants generated by GPT-4, Claude Haiku, and Anthropic Opus. For both human and LLM samples, spreading activation was modeled from participants’ ERT words within a human-derived semantic network, enabling a direct comparison of structural activation dynamics rather than psychological states. Humans with higher distress scores exhibited stronger, faster, and more persistent activation of negative concepts, supporting theories of rumination and memory bias. GPT-4 approximated human-like trajectories most closely, though with reduced variability. Study 2 linked recall dynamics with the Big Five traits, confirming that neuroticism predicted greater activation of negative concepts, while extraversion acted as a protective factor. While LLMs lack autobiographical memory, their semantic activation partially mirrored human associations. These findings demonstrate that network-based spreading activation analysis can reveal cognitive signatures of distress while also highlighting the limits of LLMs in modeling human affect. Full article

Electronic word of mouth (eWOM) is a powerful form of online communication that strongly influences consumer purchasing behaviour. However, what remains less clear is the combined influence of situational factors versus personality traits when assessed simultaneously. The aim of this paper is to address this gap by developing an integrative conceptual model to assess the comparative relevance of situational factors and personality traits in driving eWOM generation in the Romanian accommodation sector. To implement the research scope, an empirical, quantitative, questionnaire-based investigation was pursued, data being collected from 291 tourists who had previous experience with online accommodation platforms such as booking.com, Airbnb, Trivago, etc. Based on the proposed conceptual model, data were analysed by means of structural equation modelling via SmartPLS 4.0. The research extends previous knowledge based on the Theory of Reasoned Action (TRA) and the Theory of Cognitive Dissonance (TCD), showing the combined multiple effects of situational factors and personality traits on consumers’ behaviour in generating eWOM in the accommodation sector. The results show that acquisition regret strongly drives eWOM generation intention, this regret being significantly increased by the unpleasantness, unacceptability, and importance of the consumer’s situation. Consumer expressivity predicts eWOM generation and is positively influenced by perceived social support, a relationship newly validated in the literature. Full article

Background: Previous research has found an association between attractiveness and personality traits, but the neural mechanisms are largely unknown. Method: We used a Stroop-like paradigm combined with EEG recordings to investigate how personality traits affect the perception of facial and vocal attractiveness. Twenty-three female participants classified the attractiveness of male faces and male voices paired with positive or negative personality trait words. Results: The behavioral results indicate that personality trait words that are semantically congruent with attractiveness levels facilitate the perception of attractiveness, whereas incongruent trait information produces the opposite effect. Event-related potentials revealed that the influence of personality trait words on facial attractiveness was primarily related to motivated attention as indicated by the late positive component. In the voice task, personality trait words impacted vocal attractiveness processing first during semantic integration (N400 component) and then modulated motivated attention. Conclusions: These results suggest that alleged personality traits modify attractiveness processing in faces and voices in relatively late and partially modality-specific stages. Full article

We study the emergence of agency from scratch by using Large Language Model (LLM)-based agents. In previous studies of LLM-based agents, each agent’s characteristics, including personality and memory, have traditionally been predefined. We focused on how individuality, such as behavior, personality, and memory, can be differentiated from an undifferentiated state. The present LLM agents engage in cooperative communication within a group simulation, exchanging context-based messages in natural language. By analyzing this multi-agent simulation, we report valuable new insights into how social norms, cooperation, and personality traits can emerge spontaneously. This paper demonstrates that autonomously interacting LLM-powered agents generate hallucinations and hashtags to sustain communication, which, in turn, increases the diversity of words within their interactions. Each agent’s emotions shift through communication, and as they form communities, the personalities of the agents emerge and evolve accordingly. This computational modeling approach and its findings will provide a new method for analyzing collective artificial intelligence. Full article

This study investigates the impacts of the Big Five personality traits and propensity to trust on the use and writing of online reviews. Additionally, this study examines how gender moderates these impacts. Results of a survey (n = 840) show that openness to experience and conscientiousness positively influence online review use, while openness to experience and extraversion positively influence online review writing. Moreover, gender moderates the impacts of extraversion, openness to experience, and agreeableness on online review writing, with no moderating effect observed for online review use. Our findings contribute to the electronic word-of-mouth (eWOM) literature and offer important practical insights for eWOM platforms. Full article

Trust and distrust are constructs that have provoked and undergone lots of discussion in the fields of sociology and psychology. However, to our knowledge, there is little agreement about how these constructs should be treated in the future. The present study tries to help in this discussion by re-analyzing prior neurophysiological data highlighting differences between trust and distrust by connecting these data with two distinct personality dimensions. Thus, the objective was to analyze the connection between neurophysiological trust/distrust processing and distinct HEXACO personality dimensions. Differences were found in the event-related potentials (ERPs) calculated for visual presentations of political institution words and brand names, which were evaluated with respect to trust and distrust by button presses. Two time points (330 ms and 780 ms) showed brain activity differences between trust and distrust related to the two word categories at frontal electrode locations. For this study, these findings were taken and connected to HEXACO-60 personality inventory results collected from prior participants. Statistical analysis revealed a significant interaction between the ERPs and two HEXACO personality dimensions concerning trusted brands at the later time point (780 ms) at the right frontal electrode location F8. This result is taken as neurophysiological evidence that parameter values of the personality traits honesty–humility and agreeableness have an influence on brain functions related to trusted brands. Full article

Vocabulary acquisition and retention is an essential part of learning a foreign language and many learners use flashcard applications to repetitively increase vocabulary retention. However, it can be difficult for learners to remember new words and phrases without any context. In this paper, we propose a system that allows users to acquire new vocabulary with media which gives context to the words. Theoretically, this use of multimedia context should enable users to practice with interest and increased motivation, which has been shown to enhance the effects of contextual language learning. An experiment with 46 English as foreign language learners showed better retention after two weeks with the proposed system as compared to ordinary flashcards. However, the impact was not universally beneficial to all learners. An analysis of participant attributes that were gathered through surveys and questionnaires shows a link between personality and learning traits and affinity for learning with this system. This result indicates that the proposed system provides a significant advantage in vocabulary retention for some users, while other users should stay with traditional flashcard applications. The implications of this study indicate the need for the development of more personalized learning applications. Full article

This paper analyzes the cases wherein a previously unknown and unique mythological character (with his/her specific behavior, “personal” traits, appearance, origin, etc.) is generated by a cultural linguistic sign or a fragment of text. This research is based on the Russian cultural and linguistic tradition, mainly in its dialectal version (the language of Russian peasants). Its sources include data published in the late 19th–early 21st century in dictionaries of Russian dialects and, primarily, the unpublished field materials of the Ural Federal University Toponymic Expedition, covering data from the Russian North, the Urals, and the Volga region. According to their nature or origin, the names of characters studied in this paper derive from two types of linguistic signs: (1) Names based on usual forms of standard vocabulary that can be both proper and common nouns; the former may refer to various categories, such as toponyms (names of geographical objects), chrononyms (names of calendar dates), hagionyms (names of saints), names of icons, etc. (2) Names originating from a text, usually folkloric; these are word combinations or phrases that only act as a single unit within their “parent” text. Sometimes, but less often, these consist of one word that is of key importance in the source text. Such a phrase or word can migrate outside the “parent” text or genre, expanding their lexical combinability and changing their syntactic regime to become a name of a mythological character. It takes two sources of motivation for a new character to emerge—a linguistic (a word that seeks a new context) and a cultural one (a semiotically intense context, such as a situation associated with danger, prohibition, omens, aggression, or magical practices). The combination of these incentives is not uncommon, so the stock of mythology used for names is being constantly renewed. Full article

Scarcity refers to a state in which an individual’s resources do not satisfy his/her needs. A sense of scarcity evokes negative emotions. A fundamental strategy for coping with this negative threat is for people to emphasize the desirability of their personal traits. In this study, a 2 (sense of scarcity: high or low) × 2 (valence: positive or negative) mixed-design experiment was conducted to examine whether and how a sense of scarcity affected one’s self-evaluation. Participants were assigned randomly to a high- or low-scarcity group. The chances of assistance rendered to an individual during a word puzzle task were manipulated to induce a high or low sense of scarcity. Then, participants were asked to make positive and negative trait judgments of themselves compared with their average peers. The results showed that people judged their personalities to be more desirable (i.e., more positive and less negative traits) than their average peers, manifesting the above-average effect. More importantly, people with a high sense of scarcity manifested a greater above-average effect than those with a low sense of scarcity. This study suggests that people could highlight their positive aspects to cope with predicaments in social life. Full article

Persons working in tactical occupations are often exposed to high-stress situations. If this stress is to be measured, an understanding of the stress outcomes used in these occupations is needed. The aim of this review was to capture and critically appraise research investigating subjective and objective outcome measures of physiological stress in tactical occupations. Several literature databases (PubMed, EMBASE, EBsco) were searched using key search words and terms. Studies meeting inclusion criteria were critically evaluated and scored by two authors using the Joanne Briggs Institute (JBI) critical appraisal tool. Of 17,171 articles, 42 studies were retained. The Cohen’s Kappa agreement between authors was 0.829 with a mean JBI Score of included studies of 8.1/9 ± 0.37 points. Multiple subjective and objective measures were assessed during a variety of high-stress tasks and environments across different occupations, including police officers, emergency service personnel, firefighters, and soldiers in the military. Common objective outcomes measures were heart rate, cortisol, and body temperature, and subjective measures were ratings of perceived exertion, and the Self Trait Anxiety Inventory. Often used in combination (i.e., subjective and objective), these outcome measures can be used to monitor stressors faced by tactical personnel undergoing on-the-job training. Full article

The digital era introduces significant challenges for privacy protection, which grow constantly as technology advances. Privacy is a personal trait, and individuals may desire a different level of privacy, which is known as their “privacy concern”. To achieve privacy, the individual has to act in the digital world, taking steps that define their “privacy behavior”. It has been found that there is a gap between people’s privacy concern and their privacy behavior, a phenomenon that is called the “privacy paradox”. In this research, we investigated if the privacy paradox is domain-specific; in other words, does it vary for an individual when that person moves between different domains, for example, when using e-Health services vs. online social networks? A unique metric was developed to estimate the paradox in a way that enables comparisons, and an empirical study in which $(n=437)$ validated participants acted in eight domains. It was found that the domain does indeed affect the magnitude of the privacy paradox. This finding has a profound significance both for understanding the privacy paradox phenomenon and for the process of developing effective means to protect privacy. Full article

Mobile streaming is increasingly viewed as a major advancement in the wireless industry, as it enables users to consume content without any time or space restrictions. Mobile TV serves as an excellent example of streaming, providing services for watching TV content on mobile devices. While previous studies have explored video-on-demand (VOD) purchasing factors in mobile TV, it is rare to find research examining differences based on users’ mobile TV usage types, such as subscribers and free users. Consequently, we investigated VOD purchase factors for 310 subscribers and 311 free mobile TV users. In other words, using 621 survey responses, we analyze the influence of personality traits, intrinsic and extrinsic motivations, and mobile-related factors on users’ VOD purchase intentions and behavior. Our findings indicate that mobile TV utilization, hedonic needs, and subjective norms are positively related to VOD purchases, and that neuroticism, extraversion, openness, and conscientiousness positively impact mobile TV utilization. We also examine the relationships between the constructs within two sub-groups to highlight the differing perceptions and behavioral patterns of these groups regarding mobile TV utilization and VOD purchases. Theoretical and practical implications are discussed as well. Full article