Using Named Entities for Computer-Automated Verbal Deception Detection

There is an increasing demand for automated verbal deception detection systems. We propose named entity recognition (NER; i.e., the automatic identification and extraction of information from text) to model three established theoretical principles: (i) truth tellers provide accounts that are richer in detail, (ii) contain more contextual references (specific persons, locations, and times), and (iii) deceivers tend to withhold potentially checkable information. We test whether NER captures these theoretical concepts and can automatically identify truthful versus deceptive hotel reviews. We extracted the proportion of named entities with two NER tools (spaCy and Stanford's NER) and compared the discriminative ability to a lexicon word count approach (LIWC) and a measure of sentence specificity (speciteller). Named entities discriminated truthful from deceptive hotel reviews above chance level, and outperformed the lexicon approach and sentence specificity. This investigation suggests that named entities may be a useful addition to existing automated verbal deception detection approaches.

An Investigation on the Detectability of Deceptive Intent about Flying through Verbal Deception Detection

Background:

Academic research on deception detection has largely focused on the detection of past events. For many applied purposes, however, the detection of false reports about someone’s intention merits attention. Based on the verbal deception detection paradigm, we explored whether true statements on intentions were more detailed and more specific than false statements on intentions, particularly when instructed to be as specific as possible.

Method:

Participants (n = 222) lied or told the truth about their upcoming travel plans either providing ‘as much information as possible’ (standard instructions) or being ‘as specific as possible’ (i.e., mentioning times, locations, places; specific instructions), resulting in four conditions (truthful vs. deceptive intention by standard vs. specific instructions). We collected data via a custom-made web app and performed automated verbal content analysis of participants’ written answers.

Findings:

We did not find a significant difference in the specificity of participants’ statements. The instruction to be as specific as possible promoted more specific information but did not help to discern honest from deceptive flying intentions.

Conclusion:

The experiment reported here attempted to demonstrate automated verbal deception detection of intentions. The difficulty in capturing genuine intentions, and the non-intrusive, non-interactive questioning approach might explain the null findings and raise questions for further research. We conclude with suggestions for a novel framework on semi-interactive information elicitation.

A Strong Validation of the Crosswise Model Using Experimentally-Induced Cheating Behavior

We constructed an online cheating paradigm that could be used to validate the Crosswise Model ( Yu, Tian, & Tang, 2008 ), a promising indirect questioning technique designed to control for socially desirable responding on sensitive questions. Participants qualified for a reward only if they could identify the target words from three anagrams, one of which was virtually unsolvable as shown on a pretest. Of the 664 participants, 15.5% overreported their performance and were categorized as cheaters. When participants were asked to report whether they had cheated, a conventional direct question resulted in a substantial underestimate (5.1%) of the known prevalence of cheaters. Using a CWM question resulted in a more accurate estimate (13.0%). This result shows that the CWM can be used to control for socially desirable responding and provides estimates that are much closer to the known prevalence of a sensitive personal attribute than those obtained using a direct question.

Assessing autobiographical memory: the web-based autobiographical Implicit Association Test

By assessing the association strength with TRUE and FALSE, the autobiographical Implicit Association Test (aIAT) [Sartori, G., Agosta, S., Zogmaister, C., Ferrara, S. D., & Castiello, U. (2008). How to accurately detect autobiographical events. Psychological Science, 19, 772-780. doi: 10.1111/j.1467-9280.2008.02156.x ] aims to determine which of two contrasting statements is true. To efficiently run well-powered aIAT experiments, we propose a web-based aIAT (web-aIAT). Experiment 1 (n = 522) is a web-based replication study of the first published aIAT study [Sartori, G., Agosta, S., Zogmaister, C., Ferrara, S. D., & Castiello, U. (2008). How to accurately detect autobiographical events. Psychological Science, 19, 772-780. doi: 10.1111/j.1467-9280.2008.02156.x ; Experiment 1]. We conclude that the replication was successful as the web-based aIAT could accurately detect which of two playing cards participants chose (AUC = .88; Hit rate = 81%). In Experiment 2 (n = 424), we investigated whether the use of affirmative versus negative sentences may partly explain the variability in aIAT accuracy findings. The aIAT could detect the chosen card when using affirmative (AUC = .90; Hit rate = 81%), but not when using negative sentences (AUC = .60; Hit rate = 53%). The web-based aIAT seems to be a valuable tool to facilitate aIAT research and may help to further identify moderators of the test's accuracy.

Implicit and explicit measures of spider fear and avoidance behavior: Examination of the moderating role of working memory capacity

BACKGROUND AND OBJECTIVES

Avoidance behavior is central to several anxiety disorders. The current study tested whether avoidance behavior for spiders depends on a dynamic interplay between implicit and explicit processes, moderated by the availability to exert control through working memory capacity (WMC).

METHODS

A total of 63 participants completed an approach-avoidance task, an implicit association test, a spider fear questionnaire and a behavioral avoidance test that included an assessment of approach distance as well as approach speed. WMC was measured by a complex operation span task. It was hypothesized that in individuals with low WMC, implicit avoidance tendencies and implicit negative associations predict avoidance behavior for a spider better than the explicit measure, whereas in high WMC individuals, the explicit measure should better predict avoidance behavior than the implicit measures.

RESULTS

Results revealed that WMC moderated the influence of implicit negative associations, but not implicit avoidance tendencies, on spider approach distance but not the speed of approaching. Although explicit spider fear directly influenced avoidance behavior, its impact was not modulated by WMC.

LIMITATIONS

Participants in our study were from a non-clinical sample, which limits the generalizability of our findings.

CONCLUSIONS

These findings suggest that implicit processes might become more pertinent for fear behavior as the ability to control such processes wanes, which may be particularly relevant for anxiety disorders given their association with lowered executive control functioning. As such, training procedures that specifically target implicit processes or control abilities might improve treatment outcomes for anxiety disorders.

When deception becomes easy: the effects of task switching and goal neglect on the truth proportion effect

Lying is typically more cognitively demanding than truth telling. Yet, recent cognitive models of lying propose that lying can be just as easy as truth telling, depending on contextual factors. In line with this idea, research has shown that the cognitive cost of deception decreases when people frequently respond deceptively, while it increases when people rarely respond deceptively (i.e., the truth proportion effect). In the present study, we investigated two possible underlying mechanisms of the truth proportion effect. In Experiment 1 (N = 121), we controlled for the impact of switch costs by keeping the number of switches between deceptive and truthful responses constant. We found that people who often responded deceptively made fewer errors when responding deceptively than people who only occasionally responded deceptively, replicating the truth proportion effect. Thus, while the truth proportion effect in earlier studies may be partially driven by the cost of switching between truthful and deceptive responses, we still found evidence for the truth proportion effect while controlling for switch costs. In Experiment 2 (N = 68), we assessed whether the truth proportion effect is influenced by goal neglect. According to this view, the truth proportion effect should be reduced if participants are cued to maintain the task goals, while it should be larger when participants are allowed to neglect the task goals. In line with this hypothesis, we found a smaller truth proportion effect when participants were cued with the task goals compared to when they were not cued. This study shows that the truth proportion effect is influenced by goal neglect, implying that frequent deceptive responding strengthens the goal of responding deceptively. Our findings imply that the accuracy of lie detection tests could be increased by using a majority of truth-items (i.e., induce the truth proportion effect), and that the truth proportion effect should be maximized by (1) increasing the number of truth-lie task switches and (2) inducing goal neglect.

Diagnostic value of the Dutch version of the McLean Screening Instrument for BPD (MSI-BPD)

Borderline personality disorder (BPD) often goes unrecognized, and therefore a short but accurate screening tool is desired. The present study investigated the psychometric properties of the 10-item McLean Screening Instrument for BPD (MSI-BPD) in 159 well-diagnosed female participants. The MSI-BPD showed excellent internal consistency (α = .90). When compared to BPD diagnoses based on a structured clinical interview (SCID-II), the MSI-BPD showed substantial congruent validity (receiver operating characteristic area under the curve = 0.96). The cutoff point proposed by the developers of the MSI-BPD (7 or more) showed high specificity (.96) and good sensitivity (.71). The optimal cutoff point in the present study (5 or more) showed somewhat lower specificity (.86), but importantly better sensitivity (.94). Taken together, the Dutch version of the MSI-BPD demonstrated good psychometric properties for a screening tool.

Manipulating item proportion and deception reveals crucial dissociation between behavioral, autonomic, and neural indices of concealed information

Developed as an alternative to traditional deception detection methods, the concealed information test (CIT) assesses recognition of critical (e.g., crime-relevant) "probes." Most often, recognition has been measured as enhanced skin conductance responses (SCRs) to probes compared to irrelevant foils (CIT effect). More recently, also differentially enlarged reaction times (RTs) and increased neural activity in the bilateral inferior frontal gyrus, the right middle frontal gyrus, and the right temporo-parietal junction have been observed. The aims of the current functional magnetic resonance imaging (fMRI) study were to (1) investigate the boundary conditions of the CIT effects in all three measures and thereby (2) gain more insight into the relative contribution of two mechanisms underlying enhanced responding to concealed information (i.e., orienting versus response inhibition). Therefore, we manipulated the proportion of probe versus irrelevant items, and whether suspects were instructed to actively deny recognition of probe knowledge (i.e., deceive) during the test. Results revealed that whereas overt deception was not necessary for the SCR CIT effect, it was crucial for the RT and the fMRI-based CIT effects. The proportion manipulation enhanced the CIT effect in all three measures. The results indicate that different mental processes might underlie the response pattern in the CIT. While skin conductance responding to concealed information may best be explained by orienting theory, it seems that response inhibition drives RT and blood oxygen level dependent responding to concealed information.

What’s on Your Mind?

Lie detectors can be applied in a wide variety of settings. But this advantage comes with a considerable cost: False positives. The applicability of the Concealed Information Test (CIT) is more limited, yet when it can be applied, the risk of false accusations can be set a priori at a very low level. The CIT assesses the recognition of critical information that is known only by the examiners and the culprit, for example, the face of an accomplice. Large effects are obtained with the CIT, whether combined with peripheral, brain, or motor responses. We see three important challenges for the CIT. First, the false negative rate of the CIT can be substantial, particularly under realistic circumstances. A possible solution seems to restrict the CIT to highly salient details. Second, there exist effective faking strategies. Future research will tell whether faking can be detected or even prevented (e.g., using covert measures). Third, recognition of critical crime details does not necessarily result from criminal activity. It is therefore important to properly embed the CIT in the investigative process, while taking care when drawing conclusions from the test outcome (recognition, not guilt).

Reaction time measures in deception research: comparing the effects of irrelevant and relevant stimulus-response compatibility

Evidence regarding the validity of reaction time (RT) measures in deception research is mixed. One possible reason for this inconsistency is that structurally different RT paradigms have been used. The aim of this study was to experimentally investigate whether structural differences between RT tasks are related to how effective those tasks are for capturing deception. We achieved this aim by comparing the effectiveness of relevant and irrelevant stimulus-response compatibility (SRC) tasks. We also investigated whether an intended but not yet completed mock crime could be assessed with both tasks. Results showed (1) a larger compatibility effect in the relevant SRC task compared to the irrelevant SRC task, (2) for both the completed and the intended crime. These results were replicated in a second experiment in which a semantic feature (instead of color) was used as critical response feature in the irrelevant SRC task. The findings support the idea that a structural analysis of deception tasks helps to identify RT measures that produce robust group effects, and that strong compatibility effects for both enacted crimes as well as merely intended crimes can be found with RT measures that are based on the manipulation of relevant SRC.