Search results

Prediction is a critical task in targeted online advertising, where predictions better than random guessing can translate to real economic return. This study aims to use machine learning (ML) methods to identify individuals who respond well to certain linguistic styles/persuasion techniques based on Aristotle’s means of persuasion, rhetorical devices, cognitive theories and Cialdini’s principles, given their psychometric profile.

A total of 1,022 individuals took part in the survey; participants were asked to fill out the ten item personality measure questionnaire to capture personality traits and the dysfunctional attitude scale (DAS) to measure dysfunctional beliefs and cognitive vulnerabilities. ML classification models using participant profiling information as input were developed to predict the extent to which an individual was influenced by statements that contained different linguistic styles/persuasion techniques. Several ML algorithms were used including support vector machine, LightGBM and Auto-Sklearn to predict the effect of each technique given each individual’s profile (personality, belief system and demographic data).

The findings highlight the importance of incorporating emotion-based variables as model input in predicting the influence of textual statements with embedded persuasion techniques. Across all investigated models, the influence effect could be predicted with an accuracy ranging 53%–70%, indicating the importance of testing multiple ML algorithms in the development of a persuasive communication (PC) system. The classification ability of models was highest when predicting the response to statements using rhetorical devices and flattery persuasion techniques. Contrastingly, techniques such as authority or social proof were less predictable. Adding DAS scale features improved model performance, suggesting they may be important in modelling persuasion.

In this study, the survey was limited to English-speaking countries and largely Western society values. More work is needed to ascertain the efficacy of models for other populations, cultures and languages. Most PC efforts are targeted at groups such as users, clients, shoppers and voters with this study in the communication context of education – further research is required to explore the capability of predictive ML models in other contexts. Finally, long self-reported psychological questionnaires may not be suitable for real-world deployment and could be subject to bias, thus a simpler method needs to be devised to gather user profile data such as using a subset of the most predictive features.

The findings of this study indicate that leveraging richer profiling data in conjunction with ML approaches may assist in the development of enhanced persuasive systems. There are many applications such as online apps, digital advertising, recommendation systems, chatbots and e-commerce platforms which can benefit from integrating persuasion communication systems that tailor messaging to the individual – potentially translating into higher economic returns.

This study integrates sets of features that have heretofore not been used together in developing ML-based predictive models of PC. DAS scale data, which relate to dysfunctional beliefs and cognitive vulnerabilities, were assessed for their importance in identifying effective persuasion techniques. Additionally, the work compares a range of persuasion techniques that thus far have only been studied separately. This study also demonstrates the application of various ML methods in predicting the influence of linguistic styles/persuasion techniques within textual statements and show that a robust methodology comparing a range of ML algorithms is important in the discovery of a performant model.

Leader self-efficacy (LSE) is a construct studied in adults and college students which is associated with leader emergence, individual performance, and group performance.However, to date, it has not been heavily examined in youth.Therefore, a five-item youth LSE scale was created which can aid in further research of this construct.This holds significant implications for future educational initiatives, research, and the development of the next generation of leaders.

This study aims to explore how and why self-discrepancy affects materialism and impulsive buying and the extent to which subjective well-being mediates the relationship between self-discrepancy, materialism and impulsive buying.

The authors have tested the hypothesis with a convenience sample (N = 434) from Lithuania. Descriptive analysis, principal components analysis (PCA), serial mediation hypothesis tested with model 81 from regression-based path analysis modeling tool PROCESS Macro for IBM® SPSS® Statistics 24.7 statistical software.

The serial and parallel mediation analysis results indicated that greater self-discrepancy was related to poorer life satisfaction, which was related to greater materialism centrality, which promoted greater impulsive buying. Also, the greater the self-discrepancy, caused more occurrence of negative affect, which relates to increased materialism happiness, which triggers impulsive buying. Self-discrepancy was negatively associated with the frequency of positive affect, which was positively related to materialism, which stimulates impulsive buying.

The study was dominated by younger respondents. The survey was conducted during the lockdown of the Covid-19 virus pandemic.

There is little empirical evidence to support the reasoning behind why self-discrepancy predicts a higher degree of materialism, which increases impulsive buying. This study suggests the mechanism of how subjective well-being affects relationships of self-discrepancy on materialism and impulsive buying.

Psychometric analyses of self-administered questionnaire data tend to focus on items and instruments as a whole. The purpose of this paper is to investigate the functioning of the response scale and its impact on measurement precision. In terms of the response scale direction, existing evidence is mixed and inconclusive.

Three experiments are conducted to examine the functioning of response scales of different direction, ranging from agree to disagree versus from disagree to agree. The response scale direction effect is exemplified by two different latent constructs by applying the Rasch model for measurement.

The agree-to-disagree format generally performs better than the disagree-to-agree variant with spatial proximity between the statement and the agree-pole of the scale appearing to drive the effect. The difference is essentially related to the unit of measurement.

A careful investigation of the functioning of the response scale should be part of every psychometric assessment. The framework of Rasch measurement theory offers unique opportunities in this regard.

Besides content, validity and reliability, academics and practitioners utilising published measurement instruments are advised to consider any evidence on the response scale functioning that is available.

The study exemplifies the application of the Rasch model to assess measurement precision as a function of the design of the response scale. The methodology raises the awareness for the unit of measurement, which typically remains hidden.

The purpose of this viewpoint paper is to explore middle leaders' ability to recognise emotions in the context of workplace research, and to propose measures that might support them in their role.

This paper combines a contemporary literature review with reflections from practice to develop more nuanced understandings of middle leadership. This paper applied the Geneva Emotional Recognition Test (GERT) to explore the level of emotional recognition of 86 individuals (teachers to headteachers (equivalent to school principals)).

The preliminary findings suggest that teachers and headteachers have higher levels of emotional recognition than middle and senior leaders. This paper subsequently argues that the task-orientated nature middle leadership compounds an individual's ability to engage effectively in relationship-orientated tasks. This explains why middle leaders scored lower on the GERT assessment. This is further inhibited by the anti-correlation in the brain's ability to deal with the task-positive network (TDM) and default mode network (DMN) processing functions where individuals operate in one neural mode for long periods.

The viewpoint paper proposes a number of implications for middle leaders and suggests that middle leaders should proactively seek out opportunities to be engaged in activities that support the DMN function of the brain and subsequently the relationship-orientated aspects of leadership, for example, coaching other staff members. However, it has to be recognised that the sample size is small and further work is needed before any generalisations can be made.

This paper offers a contemporary review of the role of middle leaders underpinned by a preliminary study into individuals' ability to recognise emotions.