Dialogue management in conversational agents through psychology of persuasion and machine learning

Carfora, Valentina; Massimo, Francesca Di; Rastelli, Rebecca; Catellani, Patrizia; Piastra, Marco

doi:10.1007/s11042-020-09178-w

Cited by 29 publications

(33 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the available cases did not provide evidence concerning the distinction among loss and non-loss messages. Consistent with this prior evidence, in the case of messages focused on reducing RPMC, recent studies (Di Massimo et al, 2019 ; Carfora et al, 2020b ) showed that loss-framed messages were the least persuasive, while non-loss-framed messages, focused on the possibility of avoiding the negative consequences related to high RPMC, were the most persuasive messages, able to involve and persuade the majority of receivers independent of their prior beliefs. One possible explanation of the lower persuasiveness of loss messages as compared to non-loss messages is that the former might be more likely to trigger strong negative emotions and, in turn, reactance (Brehm and Brehm, 1981 ).…”

Section: Introductionmentioning

confidence: 64%

“…Even though message framing effects have been studied extensively in communication advocating different types of health behavior (e.g., Gallagher and Updegraff, 2012 ; Rothman et al, 2020 ), most research on reducing RPMC has so far ignored the distinction among gain, non-loss, non-gain, and loss messages. Recently, Di Massimo et al ( 2019 ) and Carfora et al ( 2020b ) indeed tested the effects of these four types of messages, showing not only that they differentially influence attitude and intention toward RPMC, but also that their influence varies according to receivers' baseline attitude, intention, perceived efficacy, and subjective norm. To move further into the comprehension of the factors that may underlie the different effectiveness of the four types of messages, in the present study we explored the reactions receivers have when they are exposed to these messages, in terms of systematic and heuristic processing of the messages, positive or negative emotional reactions triggered by the messages, and message evaluation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Cognitive-Emotional Model to Explain Message Framing Effects: Reducing Meat Consumption

2021

Self Cite

View full text Add to dashboard Cite

We tested the plausibility of a cognitive-emotional model to understand the effects of messages framed in terms of gain, non-loss, non-gain, and loss, and related to the health consequences of red/processed meat consumption. A total of 544 Italian participants reported their attitude toward reduced red/processed meat consumption and intention to eat red/processed meat (time 1 questionnaire). One week later, participants were randomly assigned to four different message conditions: (a) gain messages focused on the positive health outcomes associated with low meat consumption; (b) non-loss messages focused on the avoided negative health outcomes associated with low meat consumption; (c) non-gain messages focused on the missed positive health outcomes associated with high meat consumption; (d) loss messages focused on the negative health outcomes associated with high meat consumption (message sending). After reading the messages, participants answered a series of questions regarding their emotional and cognitive reactions to the messages, their evaluation of the messages, and again their attitude and intention toward red/processed meat consumption (time 2 questionnaire). Comparing different multivariate linear models under the Bayesian approach, we selected the model with the highest plausibility conditioned to observed data. In this model, message-induced fear influenced systematic processing, which in turn positively influenced message evaluation and attitude, leading to reduced intention to consume red/processed meat. Vice versa, message-induced anger reduced systematic processing, which in turn negatively influenced message evaluation, and led to no effect on attitude and intention. The comparison among message conditions showed that gain and non-loss messages activated integrated emotional and cognitive processing of the health recommendation, while loss and non-gain messages mainly activated emotional shortcuts toward attitude and intention. Overall, these results advance our comprehension of the effects of message framing on receivers' attitudes and intentions.

show abstract

Section: Introductionmentioning

confidence: 64%

Section: Introductionmentioning

confidence: 99%

A Cognitive-Emotional Model to Explain Message Framing Effects: Reducing Meat Consumption

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, reference to subjective norm and personal norm, in addition to providing information about the environmental impact of excessive RPMC, can be fruitful strategies to encourage people to reduce their red and processed meat consumption. The same holds for a communicative stress on both rational and emotional motives related to reduced RPMC, such as health and well-being benefits (Bertolotti, Carfora, & Catellani, 2020;Carfora, Di Massimo, Rastelli, Catellani, & Piastra, 2020), anticipated affective reactions (Carfora et al, 2018), or utilitarian and hedonic motivation (Lombardi et al, 2017).…”

Section: Discussionmentioning

confidence: 99%

Rational and moral motives to reduce red and processed meat consumption

Carfora

Conner

Caso

et al. 2020

J Applied Social Pyschol

Self Cite

View full text Add to dashboard Cite

Western diets are characterized by excessive red and processed meat consumption (RPMC), which has several environmental negative consequences, such as risky pollution, depletion, and the disruption of water and land resources (e.g., Gardner, Hartle, Garrett, Offringa, & Wasserman, 2019). To reduce these effects, public policies should effectively communicate the urgency of a shift to a less animal-based diet. However, there is little agreement over the degree to which public policies should leverage either rational or moral motives to promote the reduction of RPMC. While reference to rational motives implies that a behavior is the result of an individual cost-benefit analysis (e.g., Tobler, Visschers, & Siegrist, 2011), reference to moral motives implies that a behavior is based on pro-environmental and ethical concerns (Austgulen, Skuland, Schjøll, & Alfnes, 2018; de Boer, de Witt, & Aiking, 2016). To address this problem, more evidence on the complex relationships among psychosocial motives associated with RPMC is needed. So far, only a few scholars have considered rational and moral motives simultaneously, and this is also the case for the main psychosocial factors related to them (e.g., Siegrist, Visschers, & Hartmann, 2015; Yadav, Dokania, & Pathak, 2016). In the present study, we contribute to this debate testing the integration between two theoretical frameworks that are generally used to explain pro-environmental and food choices, namely, the Theory of Planned Behavior (TPB; Ajzen, 1991) and the Value-Belief-Norm (VBN; Stern, Dietz, Abel, Guagnanon, & Kalof, 1999). The TPB is mainly focused on a rationalbased explanation of the people's intention to perform a given

show abstract

“…The different effects of gain, non-loss, non-gain and loss messages have been studied in communication advocating different types of healthy behavior (e.g., Dijkstra et al, 2011 ; Carfora et al, 2020 ). For example, Carfora et al ( 2021 ) considered the aforementioned four types of messages to promote healthy eating and showed that they induce different message evaluations, which in turn influences attitude and intention, via a cognitive or emotional elaboration.…”

Section: Introductionmentioning

confidence: 99%

“…For example, Carfora et al ( 2021 ) considered the aforementioned four types of messages to promote healthy eating and showed that they induce different message evaluations, which in turn influences attitude and intention, via a cognitive or emotional elaboration. Besides, Carfora et al ( 2020 ) showed that gain and non-loss messages activate an integrated emotional and cognitive processing of the health recommendation, while loss and non-gain messages mainly activate emotional shortcuts toward attitude and intention. Finally, the differential influence of these four message frames on attitude and intention has been shown to vary according to some baseline psychosocial features, such as self-efficacy (e.g., Di Massimo et al, 2019 ; Carfora et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

The Effect of Persuasive Messages in Promoting Home-Based Physical Activity During COVID-19 Pandemic

Carfora

Catellani

2021

Front. Psychol.

Self Cite

View full text Add to dashboard Cite

We tested the plausibility of a persuasion model to understand the effects of messages framed in terms of gain, non-loss, loss, and non-gain, and related to the physical, mental and social consequences of doing physical activity at home during the lockdown restrictions. 272 Italian participants responded to a questionnaire on their attitude and intention at Time 1, frequency of past behavior, and self-efficacy related to exercising at home. Then, participants were randomly assigned to four different message conditions: (a) gain messages focused on the positive outcomes associated with doing physical activity at home; (b) non-loss messages focused on the avoided negative outcomes associated with doing physical activity at home; (d) loss messages focused on the negative outcomes associated with not doing physical activity at home; (c) non-gain messages focused on the missed positive outcomes associated with not doing physical activity at home. After reading the messages, participants answered a series of questions regarding their perception of threat and fear, their evaluation of the messages, and their attitude and intention toward exercising at home at Time 2. Using multigroup structural equation modeling, we compared message conditions, and tested whether the effects of the messages on attitude and intention at Time 2 were mediated by message-induced threat, message-induced fear, and message evaluation. Results showed that the perception of the messages as not threatening was the key point to activate a positive evaluation of the recommendation. The highest persuasive effect was observed in the case of the non-loss frame, which did not threaten the receivers, triggered a moderated fear and, in turn, activated a positive evaluation of the recommendation, as well as higher attitude and intention to do home-based physical activity at Time 2. Overall, these results advance our comprehension of the effects of message framing on receivers' attitudes and intentions toward home-based physical activity.

show abstract

Dialogue management in conversational agents through psychology of persuasion and machine learning

Cited by 29 publications

References 39 publications

A Cognitive-Emotional Model to Explain Message Framing Effects: Reducing Meat Consumption

A Cognitive-Emotional Model to Explain Message Framing Effects: Reducing Meat Consumption

Rational and moral motives to reduce red and processed meat consumption

The Effect of Persuasive Messages in Promoting Home-Based Physical Activity During COVID-19 Pandemic

Contact Info

Product

Resources

About