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.

Virtual assistants are increasingly used for persuasive purposes, employing the different modalities of voice and text (or a combination of the two). In this study, the authors compare the persuasiveness of voice-and text-based virtual assistants. The authors argue for perceived human-likeness and cognitive load as underlying mechanisms that can explain why voice- and text-based assistants differ in their persuasive potential by suppressing the activation of consumers' persuasion knowledge.

A pre-registered online-experiment (n = 450) implemented a text-based and two voice-based (with and without interaction history displayed in text) virtual assistants.

Findings show that, contrary to expectations, a text-based assistant is perceived as more human-like compared to a voice-based assistant (regardless of whether the interaction history is displayed), which in turn positively influences brand attitudes and purchase intention. The authors also find that voice as a communication modality can increase persuasion knowledge by being cognitively more demanding in comparison to text.

Simply using voice as a presumably human cue might not suffice to give virtual assistants a human-like appeal. For the development of virtual assistants, it might be beneficial to actively engage consumers to increase awareness of persuasion.

The current study adds to the emergent research stream considering virtual assistants in explicitly exploring modality differences between voice and text (and a combination of the two) and provides insights into the effects of persuasion coming from virtual assistants.

This paper aims to demonstrate that self-persuasion can be used as a marketing technique to increase consumers’ generosity and that the efficacy of this approach is dependent on consumers’ involvement with target behavior.

An experimental field-study was conducted to investigate the effects of self-persuasion versus direct persuasion attempts versus no persuasion attempts on consumers’ tipping behavior in a lunchroom. Additionally, in a lab experiment, the moderating role of involvement on self-persuasion versus direct persuasion was tested.

The results reveal that self-persuasion is more effective than direct persuasion attempts or no persuasive messages in increasing consumers’ generosity. This is moderated by consumers’ involvement with the target behavior. For consumers with high involvement, self-persuasion is more effective than direct persuasion, while no differences were found for consumers with moderate or low involvement.

The scope of self-persuasion is not limited to the inhibition of undesired behavior, but it also extends to the facilitation of desired behavior, which considerably broadens the scope of this technique. Self-persuasion might be used as a marketing technique to influence consumers’ purchase behavior. This might be particularly viable in situations in which consumers feel high involvement with products or behavior.

Recently, research in health psychology demonstrated that self-persuasion is a very effective way of inhibiting undesired, addictive behavior and being more successful than direct persuasion. Yet, insufficient knowledge is available about the efficacy of self-persuasion with regard to promoting other target behaviors. In particular, its potential as a marketing technique to influence consumers’ behavior and its boundary conditions are still understudied.

With the developments of the digital era and considerable developments in ICT, advertisers are leveraging data-driven forms of online advertising to target consumers individually. The present study integrates privacy concerns with the constructs from the persuasion knowledge model to investigate consumer avoidance of online behavioural advertising (OBA).

The study employed an online survey method for data collection using a sample size of 345. Reliability and validity of the measurement scales were ensured, and hypotheses developed were tested through PLS-SEM using SMART PLS.

The results show that persuasion knowledge is a significant predictor of perceived benefits, perceived risks and privacy concerns. Also, privacy concern was found to significantly mediate persuasion knowledge-avoidance behaviour and perceived risk-avoidance behaviour. On the other hand, the perceived benefit was not found significant in influencing privacy concerns for OBA.

The present study is one of the initial attempts to understand the level of knowledge Indian consumers hold about OBA and how they evaluate and respond to these data-driven forms of advertising. The current study helps advance knowledge of the field and the theories used. Future studies might look at the effect of various demographic and psychographic aspects on consumer avoidance of OBA.

As the country is shifting to digital, it becomes really important to understand the privacy concerns that people perceive in regard with the current advertising practices.

Non-technical skills are of increasing importance for safety engineers to perform their job. In their position as expert consultants, they work closely with managers. Thus, gaining management support is oftentimes crucial for safety engineers to successfully improve occupational health and safety. Drawing on organizational support theory (OST), this study investigates how safety engineers’ non-technical skills in communication and persuasion (i.e. rational and hard influence tactics) are related with their management support, and how management support is related with their individual task proficiency (ITP). The purpose of this paper is to examine the moderating role of safety engineers’ expert power in this context.

Using an online questionnaire, survey data were collected from 251 safety engineers working in Austria.

Rational influence tactics are positively related to ITP via management support, whereas hard influence tactics are not. Safety engineers’ expert power moderates the relationship between influence tactics and management support and, consequently ITP. High (vs low) expert status strengthens the positive relationship of rational influence tactics on ITP via management support. For hard influence tactics, high (vs low) expert power buffered the negative relationship of upward appeal and pressure on ITP via management support.

Safety engineers should rely on rational persuasion when cooperating with management to obtain support and improve their own performance.

This study connects the effect of influence tactics in the context of safety engineers’ work performance with OST. It demonstrates that safety engineers’ influence tactics are related to work role performance through management support and that these relationships are moderated by expert power.

Following Hovland’s persuasion theory, this paper aims to develop a conceptual model and analyzes characteristics of online political deliberation behavior from three aspects (i.e. information, situation and manager). Based on the whole interactive process of online political deliberation, this paper aims to reveal the key points that affect the response effect of the government from the persuasive perspective of online political consultation.

Based on more than 40,000 netizens’ posts and government responses from 2011 to the first half of 2019 of the Chinese political platform, this paper used the text analysis and machine learning methods to extract measurement variables of online political deliberation characteristics and the econometrics analysis method to conduct empirical research.

The results showed that the textual information, political environment and identity of the political objects affect the effectiveness of government response. Furthermore, for different position categories of political officials, the length of political texts, topic categories and emotional tendencies have different effects on the response effectiveness. Additionally, the effect of political time on the effectiveness of response differs.

The findings will help ascertain the characteristics of online political deliberation behavior that affect how effective government response is and provide a theoretical basis for why the public should express their political concerns.

Extending the elaboration likelihood model (ELM), this study investigates the impact of social media influencers (SMI) on consumer well-being (CW) as well as the influence of CW on purchase intention.

A between-subjects experiment (macro- vs mega-influencer) was conducted to assess the proposed hypotheses. A total of 190 consumers participated in the experiment, and SmartPLS 3.3 was used for multigroup analyses.

Overall, argument quality (AQ), source's credibility (SC) and influencer's kindness positively predict CW, and CW predicts purchase intention. It was also found that SC is more important when information comes from a mega-influencer, whilst kindness is essential for a macro-influencer.

The results of this study imply that CW should be an essential component of influencer marketing strategy. Marketing managers should hire credible and kind influencers who can produce quality arguments. Additionally, the selection of SMI (macro- vs mega-influencer) should be aligned with the marketing objective and type of persuasion required.

This is one of the early attempts to extend ELM by introducing influencer kindness as a peripheral cue. Moreover, the study offers novelty by examining the effects of influencer characteristics (AQ, SC and kindness) on CW and comparing these effects across macro- and mega-influencers.

藉著擴展詳儘可能性模型, 本研究擬探討網絡紅人對消費者福祉的影響, 以及消費者福祉對購買意圖的影響。

研究人員進行被試間實驗 (中網紅對大型網紅) , 以對提出的假設進行評價。190名消費者參與實驗, 研究人員使用SmartPLS 3.3 進行多群組分析。

總的來說, 論點品質、來源可信度和網紅的仁慈體貼, 均能積極預測消費者福祉, 而消費者福祉亦可預測購買意圖。研究人員亦發現, 若資訊是來自大型網紅的話, 來源可信度則更形重要, 而對中網紅來說, 仁慈體貼則是不可或缺的。

研究結果暗示, 消費者福祉應是網紅市場營銷戰略的基本要素。市場經理應僱用可靠、仁慈體貼、並能提出優質論點的網紅。而且, 網絡紅人 (中網紅對大型網紅) 的挑選, 必須與營銷目標和說服的種類互相協調。

本研究為早期的嘗試, 利用引進網絡紅人的仁慈體貼作為周邊線索, 來擴展詳儘可能性模型。另外, 本研究探討網絡紅人的特徵 (論點品質、來源可信度和仁慈體貼) 會如何影響消費者福祉; 研究人員亦跨中網紅和大型網紅, 對這些影響進行比較, 就此而言, 本研究提供了創新的研究意念。

This study aims to explore how online reviews and users’ social network centrality interact to influence idea popularity in open innovation communities (OICs).

This study used Python to obtain data from the LEGO Innovation Community. In total, 285,849 reviews across 4,475 user designs between March 2019 and March 2021 were extracted to test this study’s hypotheses.

The ordinary least square regression analysis results show that review volume, review valence, review variance and review length all positively influence idea popularity. In addition, users’ in-degree centrality positively interacts with review valence, review variance and review length to influence idea popularity, while their out-degree centrality negatively interacts with such effects.

Drawing on the interactive marketing perspective, this study employs a large sample from the LEGO community and examines user design and idea popularity from a community member’s point of view. Moreover, this study is the first to confirm the role of online reviews and user network centrality in influencing idea popularity in OICs from a social network perspective. Furthermore, by integrating social network analysis and persuasion theories, this study confirms the interaction effects of review characteristics and users’ social network centrality on idea popularity.

This study’s results highlight that users should actively interact and share with reviewers their professional product design knowledge and/or the journey of their design to improve the volume of reviews on their user designs. Moreover, users could also draw more attention from other users by actively responding to heterogeneous reviews. In addition, users should be cautious with the number of people they follow and ensure that they improve their in-degree rather than out-degree centrality in their social networks.

This study integrates social network analysis and persuasion theories to explore the effects of online reviews and users’ centrality on idea popularity in OICs, a vital research issue that has been overlooked.

The purpose of this paper is to investigate practices of argumentation on Twitter discussions about climate change.

Conversational threads were collected from the Twitter API. Fundamental concepts from argumentation theory and linking practices were operationalised through a coding schema for content analysis. Tweets were analysed in the context of the discussions and coded according to their argumentative approach, interaction type and argumentation stage. Linked and embedded sources were analysed in order to find how they were used in arguments, the plausibility and soundness of the message, the consistency and trustworthiness of the linked source and its adequacy with the target audience.

Among the interactions between arguers, this study found five typical practices and several patterns involving the dynamics of the conversations, the strategy of the argumentation and the linking practices. Although the rhetorical approach was prominent, the agreement was rarely achieved. The arguers used a variety of sources to justify or support their positions, often embedding non-textual content. These linking practices, together with the strategy adopted and the topics discussed, suggest the involvement of a multiple audience engaged in discussing ad lib scientific artefacts, topics and outputs.

While Twitter has been the focus for many research papers, the conversational threads have been given little attention so far. With the Twitter API making conversations more accessible for research, this paper does not only give insight into multiple audience group argumentation dynamics but also provides a method to study the conversations from an argumentation theory perspective.

This paper aims to examine a two-way interaction between social influencers’ number of followers (micro vs meso) and argument quality (weak vs strong) on consumers’ self-reported and brain responses to advertising posts on Instagram. Further, drawing upon source credibility theory and contemporary theories of persuasion, the Instagram users’ perceptions of the influencer’s credibility are predicted to mediate the hypothesized effects.

Through an online (N = 192) and a lab study (N = 112), the authors examined Instagram users’ responses to an advertising post from Instagram influencers in terms of perceived source credibility and electronic word-of-mouth intention, using validated multi-item scales from existing literatures and electroencephalogram (EEG) measures. The hypotheses were tested with a 2 (type of influencer: micro vs meso) × 2 (argument quality: weak vs strong) between-subject design using mediated moderated linear regression analysis.

The results highlight that meso-influencers are perceived as a credible source of information only when their product-related post provides strong argument quality. Moreover, this process involves an increase in users’ cognitive work (measured with EEG), with possible implications on marketing communication strategies and online message design.

The limitations of the work can serve as ideas for future research. First, this study did not account for the influencer’s relevance and resonance. Second, the authors studied consumer responses to online communication produced by Instagram influencers within a single product category. Another important product type distinction that requires further attention is between hedonic and utilitarian products. Finally, the two studies only used positive review content. Further research should study how consumers evaluate the source credibility of a micro- vs meso-influencer when they are exposed to negative reviews containing weak vs strong arguments.

The results suggest that marketers should carefully consider Instagram influencers based on the trade-offs between credibility and reach. Specifically, micro-influencers are perceived as more credible sources of information than meso-influencers, which means that they have greater potential to affect Instagram users’ behavior. Moreover, the results suggest that meso-influencers should leverage argument quality to enhance their credibility and draw greater positive outcomes for the products and brands they endorse.

To the best of the authors’ knowledge, this study is the first to investigate how the interaction between the type of social media influencer and the argument quality affects consumers’ self-reported and brain responses to advertising posts on Instagram. Moreover, using neuroscience, this study aims to shed light on the neurophysiological processes that drive consumer responses to product-related communication posted by different influencer types.