The study evaluated the questions used in a polygraph test. It focused on criminal investigative tests (also referred to as “criminal specific tests”), those tests conducted when a criminal offence has been committed and the in-test phase questions (those test questions asked to address what is under investigation). To conduct a successful criminal investigative polygraph test, it is important that polygraphists be familiar with the types of questions used in a polygraph test and how they should be formulated for more effective outcomes. The recognition of these questions and how they are formulated is of utmost importance as it determines the success of the criminal investigative polygraph test. / Police Practice / M.Tech. (Forensic Investigation)

Automatic deception detection is an important problem with far-reaching implications in many areas, including law enforcement, military and intelligence agencies, social services, and politics. Despite extensive efforts to develop automated deception detection technologies, there have been few objective successes. This is likely due to the many challenges involved, including the lack of large, cleanly recorded corpora; the difficulty of acquiring ground truth labels; and major differences in incentives for lying in the laboratory vs. lying in real life. Another well-recognized issue is that there are individual and cultural differences in deception production and detection, although little has been done to identify them. Human performance at deception detection is at the level of chance, making it an uncommon problem where machines can potentially outperform humans. This thesis addresses these challenges associated with research of deceptive speech. We created the Columbia X-Cultural Deception (CXD) Corpus, a large-scale collection of deceptive and non-deceptive dialogues between native speakers of Standard American English and Mandarin Chinese. This corpus enabled a comprehensive study of deceptive speech on a large scale. In the first part of the thesis, we introduce the CXD corpus and present an empirical analysis of acoustic-prosodic and linguistic cues to deception. We also describe machine learning classification experiments to automatically identify deceptive speech using those features. Our best classifier achieves classification accuracy of almost 70%, well above human performance. The second part of this thesis addresses individual differences in deceptive speech. We present a comprehensive analysis of individual differences in verbal cues to deception, and several methods for leveraging these speaker differences to improve automatic deception classification. We identify many differences in cues to deception across gender, native language, and personality. Our comparison of approaches for leveraging these differences shows that speaker-dependent features that capture a speaker's deviation from their natural speaking style can improve deception classification performance. We also develop neural network models that accurately model speaker-specific patterns of deceptive speech. The contributions of this work add substantially to our scientific understanding of deceptive speech, and have practical implications for human practitioners and automatic deception detection.

published_or_final_version / abstract / toc / Sociology / Master / Master of Philosophy

Thesis (LL. M.)--Judge Advocate General's School, United States Army, 1990. / "April 1990." Typescript. Includes bibliographical references (24 leaves at end). Also issued in microfiche.

Thesis (LL. M.)--Judge Advocate General's School, United States Army, 1993. / "April 1993." Typescript. Includes bibliographical references (leaves 72-97). Also issued in microfiche.

The study evaluated the questions used in a polygraph test. It focused on criminal investigative tests (also referred to as “criminal specific tests”), those tests conducted when a criminal offence has been committed and the in-test phase questions (those test questions asked to address what is under investigation). To conduct a successful criminal investigative polygraph test, it is important that polygraphists be familiar with the types of questions used in a polygraph test and how they should be formulated for more effective outcomes. The recognition of these questions and how they are formulated is of utmost importance as it determines the success of the criminal investigative polygraph test. / Police Practice / M.Tech. (Forensic Investigation)

This dissertation, which is both exploratory and descriptive in nature, initially describes the development of the polygraph against a background of understanding society's rejection of the lying phenomenon. The theoretical foundations of polygraph thinking are then presented as forerunner to practical illustration of polygraph use in the private sector. The criminal justice system represents the sphere of polygraph ulitization central to the research. With strong American accent, polygraph use in all four components of the system is described in such a manner so as to provoke thought on the part of criminal justice functionaries as to polygraph possibilities in the execution of their functions. Research findings and recommendations aimed at stimulating thought and improvement in the field of polygraphy conclude the dissertation. / Criminology / M.A (Penology)

This dissertation, which is both exploratory and descriptive in nature, initially describes the development of the polygraph against a background of understanding society's rejection of the lying phenomenon. The theoretical foundations of polygraph thinking are then presented as forerunner to practical illustration of polygraph use in the private sector. The criminal justice system represents the sphere of polygraph ulitization central to the research. With strong American accent, polygraph use in all four components of the system is described in such a manner so as to provoke thought on the part of criminal justice functionaries as to polygraph possibilities in the execution of their functions. Research findings and recommendations aimed at stimulating thought and improvement in the field of polygraphy conclude the dissertation. / Criminology and Security Science / M.A (Penology)

LL.M. (Labour Law) / Commentators have warned that when men are given absolute control over their fellow men, there is the danger that what appeared pragmatically desirable may become morally intolerable. The current usage of polygraph testing by employers undoubtedly confirms this. In what follows, it will be argued that there is a serious shortcoming in South African law in that there is no legislative framework that governs and regulates the use of polygraph testing in the workplace. It is fairly likely that many South African employers will at some time be faced with dishonesty or criminal activities, such as fraud or theft, without accurately being able to identify where, how, and by whom such dishonesty was committed. If dishonesty and criminal activities are not properly managed, there may be adverse ramifications. As a result, many employers have opted to insert a clause in the employment offer and employment contract that relates to security obligations on the part of the employees or prospective employees. The clause would normally read as follows: “The company may request that you subject yourself to a polygraph test before commencement of employment or if an incident has occurred or and random testing during your period of employment with the Company. The employee hereby declares that he is aware of the company polygraph policy and accepts that this policy as a term and condition of his employment. The employee undertakes to comply with the said policy in all respects and acknowledges that he is bound thereby”. Magna Alloys & Research v Ellis introduced a significant change to the Courts’ approach to restraint of trade agreements by declining to follow earlier decisions based on an English precedent that an agreement in restraint of trade is prima facie invalid and unenforceable. The implication of this decision is that a right to choose a trade, occupation, or profession freely may

This research paper has examined the validity of the Forensic Assessment Interview Technique (FAINT). FAINT is a specific interview process - accepted and in current use - integrating the works of this researcher with the works of John Reid, Richard Arther, and Avinoam Sapir. The FAINT technique involves the evaluation of nonverbal behavior, projective analysis of unwitting verbal cues, and statement analysis. The fundamental hypothesis of FAINT is that truthful and deceptive criminal suspects differ demonstrably in their nonverbal, verbal and written communication, when asked to respond to a structured format of interview questions. FAINT maintains that these differences are observable and can be quantified to allow forensic interviewers to make accurate determinations of a suspect's involvement in a crime. This research has examined the validity of the technique as measured by a traditional, unweighted 3 point scale and a weighted scoring system (an issue being researched in this paper) comparatively used for determining truth or deception. This dissertation reports the results of both scoring systems, as well as a comparison between them and the historically used Behavioral Analysis Interview (BAI) that was developed by John E. Reid. / Criminology / MA (Criminology)