Chapter 16 - Passenger Screening with Verbal and Nonverbal Cues

Past and present researches in deception detection make use of questioning to ascertain the truth and deceit in the response of the interviewee. In such questioning method, either the verbal or nonverbal cues are closely monitored and analysed to arrive at a decision. Since no single verbal or nonverbal cue is able to reliably detect deception the research proposes to use both the verbal and nonverbal cues to detect deception. Therefore, this research aims to develop a Support Vector Machine and Decision Tree Model to classify the extracted verbal, nonverbal and VerbNon features as deceptive or truthful. The verbal cues capture the speech of the suspect while the nonverbal cues capture the facial expressions of the suspect. The Praat (a tool for speech analysis) was used in extracting all the verbal cues while the nonverbal features were extracted using the Active Shape Model (ASM). The work was implemented in 2015a MatLab. The analysis of the result shows that Decision Tree performs better than SVM in the classification with a percentage score of 93.5% for Nonverbal cues as against that of SVM having percentage score of 91.9%. For verbal and VerbNon cues, Decision Tree recorded 89.9% and 97.6% accuracy while SVM recorded 89.2% and 97.1% accuracy.

DePaulo et al.’s (2003) meta-analysis of verbal and nonverbal cues to deception showed that cues to deception are faint and unreliable. If liars do not spontaneously display diagnostic cues to deceit, a logical step is to make sure that investigators elicit or enhance such cues in interviews through specific interview technique. Such interview techniques were scarce in the nonverbal and verbal cues to deception domain, but recently researchers have developed alternative protocols that have their roots in cognition and are based on the assumption that questions can be asked that are more difficult for liars to answer than for truth tellers. They will be discussed in the first part of this article. Traditionally, lie detection in a forensic context concentrated on police-suspect interview settings. However, in the wake of high-profile international terrorist attacks, the importance of identifying terrorist networks and gathering intelligence about the activities of such groups has become paramount. Deception detection in intelligence interviews differs in several ways from deception detection in traditional police-suspect interviews and requires innovative deception research. In the second part of this article we discuss the emerging literature in this domain.

Studies conducted in patients diagnosed with borderline personality disorder (BPD) have documented a variety of anomalies concerning patients' abilities to interpret emotional signals. Attempting to clarify the bases of these anomalies, the current literature draws attention to a possible role of dysfunctional expectations, such as the expectation of social rejection. Dysfunctional expectations, however, may not only bias social interpretations, but may also focus attention on social cues most important in conveying emotional messages, such as nonverbal signals. To explore these assumptions, 30 female BPD patients were tasked to judge the valence of emotional states conveyed by combinations of verbal and nonverbal emotional cues. Compared to controls, BPD patients exhibited a negative bias in their interpretations and relied more on available nonverbal cues. Shifts in the relative importance of nonverbal cues appeared to be rooted mainly in a reduced reliance on positive verbal cues presumably deemed less credible by BPD patients.

After the report of the first case of COVID-19 in November 2019 from Hubei province of China, the disease took a pandemic form in a short span of 4 months, and the World Health Organization declared it as a pandemic on March 11, 2020. In India, the first case of COVID 19 was detected in Kerala on January 30, 2020, and by March 15, 2020, there were 107 cases. Fearing further spread, India declared complete lockdown from 24th March, 2020 initially for 21 days and it was further extended from time to time. The early curfew and lockdown by India has been successful in slowing the spread of infection. The other initiatives by the Government of India, namely closing the national and international airports, halting of public transport, screening of passengers coming from abroad, ramping up of testing facility, enforcing of social distancing, and wearing of masks, further reduced the rate of spread of COVID-19 infection. The most crucial component of the intervention by the institutions was tracking, testing, and treatment. For epidemiological mapping and contact tracing, the role of a mental health professional (MHP) as the leader is important during the early stages of prevention of COVID-19 infection. The MHPs are better equipped in contact tracing because of their skill in taking in-depth history, focusing on nonverbal cues during the session, early detection of denial of information, and they are better equipped in rapport building than their colleagues from other medical disciplines.

Criminal investigation in Mexico is performed by the investigation triad, which is made up of police and experts in different areas such as medicine and prosecutors. They all use interview and interrogation techniques to do their work. Unfortunately, in Mexico, there is no culture of training in governmental institutions responsible for investigating crimes, and results in ignorance of techniques for obtaining objective and reliable information that guarantees the protection of fundamental rights. This chapter illustrates the scope and limits of interview and interrogation techniques and their objectives, with emphasis on the cognitive interview (CI). The CI, which has been validated scientifically, is one of the best tools to obtain useful information, that is, results of a CI that have been conducted in the field can be used in a court of law. This technique can be used with victims, witnesses, or suspects. The current chapter also describes the most utilized techniques, cognitive interview, mnemonic techniques, Strategic Use of Evidence, and Verifiability Approach.

Determining social power: Do Chinese preschoolers integrate verbal and nonverbal cues?

When people are engaged in any interaction, they are likely to respond to each other's verbal and nonverbal cues. This responsiveness is a critical factor in the notion of rapport. In this paper, the author argues that the same human dynamics that govern everyday conversations are at play between participants in institutionalized conversations such as classroom discourse. The purpose of this study is to develop critical aspects of "conversational involvement" (Duranti, 1986; Goodwin, 1986; Gumperz, 1982; Tannen, 1985) as rapport-building devices and to provide observable phenomena that characterize rapport with participants' verbal and nonverbal cues in informal and formal conversation. In this study, nine people participated: a Korean professor of an elementary Korean language class at a major US university and eight undergraduate students whose first language is English. Three fifty-minute classroom sessions were videotaped, and segments that illustrated the teacher's and students' behaviors that facilitated rapport were transcribed and qualitatively analyzed. The author recorded the frequency of the teacher's verbal and nonverbal cues that appeared to foster rapport. This study found that the teacher shared small talk in informal before-class conversations by bringing up insignificant details about daily life. The teacher played the role of teacher during class by directing a lesson. However, she continued to utilize various rapport-building devices through selected verbal and nonverbal cues to engage her students in the conversation. In this classroom, as in everyday conversation, the participants demonstrated their desire to listen to, be responsive to, and be influenced by individuals in a certain way. The participants were part and parcel of achieving their goals in the classroom. The participants created a certain alignment to achieve their goals and signal that they were involved in the interaction. Then, the students would be able to learn the target language more through the involvement of the classroom activity, which is one of the outcomes of good rapport.

Perception of irony has been observed to be impaired in adults with autism spectrum disorder. In typically developed adults, the mismatch of verbal and nonverbal emotional cues can be perceived as an expression of irony even in the absence of any further contextual information. In this study, we evaluate to what extent high functioning autists perceive this incongruence as expressing irony. Our results show that incongruent verbal and nonverbal signals create an impression of irony significantly less often in participants with high-functioning autism than in typically developed control subjects. The extent of overall autistic symptomatology as measured with the autism-spectrum questionnaire (AQ), however, does not correlate with the reduced tendency to attribute incongruent stimuli as expressing irony. Therefore, the attenuation in irony attribution might rather be related to specific subdomains of autistic traits, such as a reduced tendency to interpret communicative signals in terms of complex intentional mental states. The observed differences in irony attribution support the assumption that a less pronounced tendency to engage in higher order mentalization processes might underlie the impairment of pragmatic language understanding in high functioning autism.

Accurately identifying another person's emotional state is an ability that may be necessary for a psychotherapist to empathize with a patient and that may be required for obtaining valid and reliable psychotherapy process ratings in research. Accuracy of identifying emotions and of rating emotional intensity expressed by a patient was studied in a comparison of 36 experienced therapists and 36 undergraduate psychology students who intended to become psychotherapists. Representative segments of a psychotherapy session were presented in one of three ways to tease apart the relative importance of verbal and nonverbal cues in making accurate ratings. Accuracy was judged against ratings supplied by two experienced and prestigious clinicians based on the same therapy sample. Results indicated that although therapists were more accurate than nontherapists in identifying emotions, they did not differ in the accuracy of rating emotional intensity. Moreover, accuracy of ratings was found to be less reliant on verbal cues among psychotherapists than among nontherapists. Finally, levels of participants' personal awareness of their own emotions had a positive impact on the accuracy of identifying specific emotions but not on the accuracy of rating their intensity. © 1999 John Wiley & Sons, Inc. J Clin Psychol 55: 39–57, 1999.

Interactive agents are becoming increasingly common in many application domains, such as education, healthcare and personal assistance. The success of such embodied agents relies on their ability to have sustained engagement with their human users. Such engagement requires agents to be socially intelligent, equipped with the ability to understand and reciprocate both verbal and non-verbal cues. While there has been tremendous progress in verbal communication, mostly driven by the success of speech recognition and question-answering, teaching agents to appropriately react to facial expressions has received less attention. In this paper, we focus on non-verbal facial cues for face-to-face communication between a user and an embodied agent. We propose a method that automatically learns to update the agent's facial expressions based on the user's expressions. We adopt a learning scheme and train a deep neural network on hundreds of videos, containing pairs of people engaging in a conversation, and without external human supervision. Our experimental results show the efficacy of our model in sustained long-term prediction of the agent's facial landmarks. We present comparative results showing that our model significantly outperforms baseline approaches and provide insightful human studies to better understand our model's qualitative performance. We release our dataset to further encourage research in this field.

Chapter 19 - Passenger Screening With Verbal and Nonverbal Cues

PurposeExperimental research on lie detection has indicated that accuracy rates hover around chance but that police are significantly better in detecting deception in “high” stakes rather than “low” stakes situations. This paper has three objectives: to compare confidence levels in lie detection for property crime and violent crime detectives; to compare differences in confidence levels for custodial and noncustodial interviews; and to evaluate the relationship between interrogation techniques and lie detection confidence.Design/methodology/approachThe study uses self‐report data from a sample of Texas police detectives.FindingsThe results of this study show that property crime detectives are significantly more confident in their lie detection ability than are violent crime detectives. The results also highlight the fact that police detectives are significantly less confident in their lie detection abilities when the suspect has been provided his or her Miranda warnings.Originality/valueThe study highlights the disparity in findings derived from self‐reported data and experimental studies on veracity judgments and the need to account for contextual factors that ultimately impact the ecological validity of this research.

The next paradigm for social and collaborative VR applications is heavily based on the real time behavior of tracked avatars for rich communication. Industry giants are actively focusing on producing photo-realistic avatars with facial and body movement tracking of real time captured verbal and non-verbal cues. This enables applications to convey the user's actual emotive expressions and behaviors through a virtual avatar, enabling the exchange of rich communication. However, the capability exposes individualized patterns of users without providing any opportunity to filter out undesired tracking before expressing them in front of a crowd, and thus can expose privacy problems. In order to address the trade-off between rich communication and privacy in VR, my PhD dissertation is focusing on providing rich user behaviors using verbal and non-verbal cues through VR avatars, while also providing a protective layer to eliminate unwanted or unneeded leaking of emotions or movements, and thus providing a more-trusted collaborative VR experience.

Pre-IPO Meetings and Analyst Consensus Building

Scholars of transportation and homeland security have begun to assess the relative costs and benefits of specific national security programs. Two programs that have generated significant attention in both popular media and scholarly literature are the Department of Homeland Security’s “Future Attribute Screening Technology” (FAST) and Transportation Security Administration’s “Screening of Passengers by Observation Techniques” (SPOT). Both of these programs utilize behavioral detection techniques to assess risk by reading the intentions of individuals. This article makes two contributions to this debate. First, it delineates the various strategies of behavioral detection that are often conflated and presents a structure of approaches, reviewing the respective literatures on each to understand the effectiveness and drawbacks of each strategy. Second, to the extent that we have sufficient knowledge about each strategy in the public realm, the article assesses the benefits, both current and potential, of each of the strategies and provides a general sense of the value of behavioral detection.