Spelling suggestions: "subject:"credibility assessment"" "subject:"credibility essessment""
1 |
Toward Enhancing Automated Credibility Assessment: A Model for Question Type Classification and Tools for Linguistic AnalysisMoffitt, Kevin Christopher January 2011 (has links)
The three objectives of this dissertation were to develop a question type model for predicting linguistic features of responses to interview questions, create a tool for linguistic analysis of documents, and use lexical bundle analysis to identify linguistic differences between fraudulent and non-fraudulent financial reports. First, The Moffitt Question Type Model (MQTM) was developed to aid in predicting linguistic features of responses to questions. It focuses on three context independent features of questions: tense (past vs. present vs. future), perspective (introspective vs. extrospective), and abstractness (concrete vs. conjectural). The MQTM was tested on responses to real-world pre-polygraph examination questions in which guilty (n = 27) and innocent (n = 20) interviewees were interviewed. The responses were grouped according to question type and the linguistic cues from each groups' transcripts were compared using independent samples t-tests with the following results: future tense questions elicited more future tense words than either past or present tense questions and present tense questions elicited more present tense words than past tense questions; introspective questions elicited more cognitive process words and affective words than extrospective questions; and conjectural questions elicited more auxiliary verbs, tentativeness words, and cognitive process words than concrete questions. Second, a tool for linguistic analysis of text documents, Structured Programming for Linguistic Cue Extraction (SPLICE), was developed to help researchers and software developers compute linguistic values for dictionary-based cues and cues that require natural language processing techniques. SPLICE implements a GUI interface for researchers and an API for developers. Finally, an analysis of 560 lexical bundles detected linguistic differences between 101 fraudulent and 101 non-fraudulent 10-K filings. Phrases such as "the fair value of," and "goodwill and other intangible assets" were used at a much higher rate in fraudulent 10-Ks. A principal component analysis reduced the number of variables to 88 orthogonal components which were used in a discriminant analysis that classified the documents with 71% accuracy. Findings in this dissertation suggest the MQTM could be used to predict features of interviewee responses in most contexts and that lexical bundle analysis is a viable tool for discriminating between fraudulent and non-fraudulent text.
|
2 |
Visualisering av trovärdighet : En undersökning av ett poängsystem som hjälpmedel vid trovärdighetsbedömningar av nyhetsartiklar på webbenJonsson, Axel, Ulenius, Magnus January 2015 (has links)
Along with the Internet and the increased flow of information that follows, it’s now a fact thateveryone have the ability to publish information that could theoretically reach hundreds ofthousands of people. Several studies point to similar problems and believe that Internet usersgenerally lack the knowledge required to assess the credibility of various web content. Thismeans that the need for a tool to help users with web credibility assessment have never beengreater. With this report we try to study the effects this kind of tool would have on the usersand to what extend they are affected by it. We have performed a quantitative survey study inwhich the majority of the questions concerning which one of two news articles therespondents considered to be the most reliable. This was done in between two groups thatwould act as control groups for one another. They were also unaware of each other’sexistence and the respondents were recruited voluntarily through Facebook. The study showsthat visual representation of articles web credibility has little to no effect on the subjectsresponses apart from two major genres. Future studies should examine these specific genresand their impact on web credibility assessment.
|
3 |
A system of deception and fraud detection using reliable linguistic cues including hedging, disfluencies, and repeated phrasesHumpherys, Sean L. January 2010 (has links)
Given the increasing problem of fraud, crime, and national security threats, assessing credibility is a recurring research topic in Information Systems and in other disciplines. Decision support systems can help. But the success of the system depends on reliable cues that can distinguish deceptive/truthful behavior and on a proven classification algorithm. This investigation aims to identify linguistic cues that distinguish deceivers from truthtellers; and it aims to demonstrate how the cues can successfully classify deception and truth.Three new datasets were gathered: 202 fraudulent and nonfraudulent financial disclosures (10-Ks), a laboratory experiment that asked twelve questions of participants who answered deceptively to some questions and truthfully to others (Cultural Interviews), and a mock crime experiment where some participants stole a ring from an office and where all participants were interviewed as to their guilt or innocence (Mock Crime). Transcribed participant responses were investigated for distinguishing cues and used for classification testing.Disfluencies (e.g., um, uh, repeated phrases, etc.), hedging words (e.g., perhaps, may, etc.), and interjections (e.g., okay, like, etc.) are theoretically developed as potential cues to deception. Past research provides conflicting evidence regarding disfluency use and deception. Some researchers opine that deception increases cognitive load, which lowers attentional resources, which increases speech errors, and thereby increases disfluency use (i.e., Cognitive-Load Disfluency theory). Other researchers argue against the causal link between disfluencies and speech errors, positing that disfluencies are controllable and that deceivers strategically avoid disfluencies to avoid appearing hesitant or untruthful (i.e., Suppression-Disfluency theory). A series of t-tests, repeated measures GLMs, and nested-model design regressions disconfirm the Suppression-Disfluency theory. Um, uh, and interjections are used at an increased rate by deceivers in spontaneous speech. Reverse order questioning did not increase disfluency use. Fraudulent 10-Ks have a higher mean count of hedging words.Statistical classifiers and machine learning algorithms are demonstrated on the three datasets. A feature reduction by backward Wald stepwise with logistic regression had the highest classification accuracies (69%-87%). Accuracies are compared to professional interviewers and to previously researched classification models. In many cases the new models demonstrated improvements. 10-Ks are classified with 69% overall accuracy.
|
4 |
Identifying Deception Using Novel Technology-Based Approaches to Uncover Concealed InformationProudfoot, Jeffrey Gainer January 2014 (has links)
Concealing information, one of the many forms of deception, is a pervasive phenomenon as it is present in virtually every facet of interpersonal communication. In some cases, information concealment can have profound implications (e.g., insider threats in organizations, security screening at the border, and criminal interviews). New technologies are under development to aid in identifying concealed information, however, additional research is needed in three key areas to increase the feasibility of using these technologies in real-world credibility assessment contexts. First, research is needed to investigate the accuracy of new credibility assessment technologies relative to existing deception-detection systems. Demonstrating that new technologies meet or exceed detection accuracies of existing systems (e.g., the polygraph) is critical. Second, research is needed to determine if a targetless Concealed Information Test (CIT) is feasible. Existing CIT research supports the presence of main effect differences between persons concealing information and the control group. These behaviors may permit the detection of concealed information without the use of customized sets of stimuli. Eliminating the need to create customized sets of stimuli for each examinee would drastically increase the ease with which an automated system can be used to conduct a CIT. Finally, research is needed to illuminate various elements of the human-computer interaction that occurs during automated credibility assessments. This is a new domain of human-computer interaction as system users in this context are not instigating the interaction, and in many cases, they may be seeking to limit the effectiveness of the system. Before novel systems designed to conduct credibility assessments can be adopted, further research is needed to illuminate how users perceive, respond to, and strategically manage their behaviors when interacting with systems of this nature. This dissertation contains the results of a research program designed to address each of these areas. First, an experiment was designed to investigate the accuracy rates of two promising noncontact measures of concealed information (oculometrics and vocalics) relative to electrodermal activity (EDA). Second, an experiment was designed to evaluate the feasibility of using a targetless CIT to elicit main effect differences between concealers and the control group to identify concealed information. And third, a thorough analysis of examinees' general perceptions, self-reported stress and arousal, perceived effort and performance, and use of countermeasures within the context of an automated credibility assessment interview was conducted. This research effort has yielded the following findings. First, eye tracking and vocalics can be used to identify significant differences in the behaviors and physiology of examinees concealing information, however, the accuracy with which truth tellers and information concealers can be classified remains impractical for an applied setting. Second, there are main effect differences between persons concealing information and telling the truth, however, the use of countermeasures may limit the accuracy with which concealers can be identified. Finally, the presence of concealed information and the use of crime-relevant questions alter how examinees perceive and react to a system designed to identify concealed information. The limitations of this research, as well as directions for future research, are discussed.
|
5 |
The Effects of an Expert System on Novice and Professional Decision Making with Application in Deception DetectionJensen, Matthew Lynn January 2007 (has links)
One effective way for organizations to capture expert knowledge and experience is to encapsulate it within an expert system (ES) and make that system available to others. While ES users have access to the system's knowledge, they shoulder the difficult task of appropriately incorporating the ES recommendations into the decision-making process.One proposed application of an ES is in the realm of deception detection. Humans are inherently poor at recognizing deception when it occurs and their confidence in their judgments is poorly calibrated to their performance. An ES has the potential to significantly improve deception detection; however, joining an ES and a human decision maker creates many important questions that must be addressed before such a system will be useful in a field environment. These questions concern changes in decision outcomes, decision processes, and the decision maker that result from ES use.To examine these questions, a prototype system was created that implements new and unobtrusive methods of deception detection. Kinesic analysis examines the body movement of a potential deceiver and linguistic analysis reviews the structure of utterances from a potential deceiver. This prototype, complete with explanations, was utilized in two experiments that examined the effects of access to the prototype, accuracy level of the prototype, user training in deception detection, and novice or professional lie-catcher status of the users.Use of the prototype system was found to significantly improve professional and novice accuracy rates and confidence alignment. Training was found to have no effect on novice accuracy rates. Accuracy level of the prototype significantly elevated accuracy rates and confidence alignment among novices; however, this improvement was imperceptible to the novices. Novices using the prototype performed on a level equivalent to professionals using the prototype. Neither professional nor novice users of the prototype exceeded the performance of the prototype system alone. Implications of these findings include emphasizing the development of computer-based tools to detect deception and defining a new role for human users of such tools.
|
6 |
A critical review of the validity of the Credibility Assessment Tool (CAT) and its application to the screening of suspected malingeringTheunissen, Karen Sunette 03 1900 (has links)
Thesis (MOccTher)-- University of Stellenbosch, 2011. / ENGLISH ABSTRACT: Malingering, the intentional simulation or exaggeration of symptoms for secondary gain, has a
significant financial impact on disability insurance given its prevalence. Multidisciplinary
professionals involved in disability determination therefore require a tool which would assist in the
screening of suspected malingerers.
AIM: The Credibility Assessment Tool (CAT), a tool which was developed as part of the
Performance APGAR, was reviewed in terms of its validity and application to the screening of
malingering. Research objectives included the review of face and content validity through a
literature review and concept analysis, as well as the review of construct and concurrent validity by
comparing the results with the operationalised malingering construct and available malingering
protocols. The adapted Slick criteria as proposed by Aronoff, applicable to chronic pain,
neurocognitive, neurological and psychiatric symptoms, was identified as the most suitable
criterion standard for use of comparison.
DESIGN: The research design was a descriptive analytical design, which was performed
retrospectively with a report review from insurance referrals to the researcher. Informed consent
was obtained from insurers who legally own the reports. A saturated sample of convenience of
184 cases with depression and pain as predominant symptoms were analysed. Recall bias were
minimised through omission of personal identifiers and the use of a peer check of 20 random
cases. Results in the peer check were suggestive of poor inter-rater reliability, rather than recall
bias.
METHOD: Cases were analysed according to the guidelines from the respective authors of the
CAT and adapted Slick criteria, however this was further defined to ensure that the study could be
replicated.
RESULTS: Face validity was adequate in terms of purpose, item selection and association
between consistency criteria, however require improvement in terms of standardised instruction
and weighting of the scale. Content validity was rated as adequate to excellent, given that it
supports criteria linked to the malingering construct. Construct validity was adequate as
demonstrated by association between concepts obtained through concept analysis. Correlation
between the CAT and adapted Slick was strong (r>0.5) however caution is expressed that this
requires further research.
CONCLUSION: Recommendations for further research included the review of content validity with
subject experts, criterion and predictive valid through a case-control study of known-groups, as
well as the reliability of the CAT, and the use of specialised ADL indices for malingering detection.
Adaptation to the CAT was depicted in the proposed Consistency Assessment Tool. / AFRIKAANSE OPSOMMING: Malingering, die opsetlike nabootsing of oordrywing van simptome vir sekondêre gewin, het ‘n
beduidende finansiële impak op ongeskiktheidsversekering as gevolg van die prevalensie daarvan.
Multidissiplinêre professionele persone betrokke by ongeskiktheidsevaluasies het daarom ‘n
meetinstrument nodig om moontlike malingeerders te identifiseer.
DOEL: Die Credibility Assessment Tool (CAT), wat ontwikkel was as deel van die Performance
APGAR, was ondersoek in terme van geldigheid en toepassing op malingering.
Navorsingsdoelwitte het die ondersoek van voorkoms- en inhoudsgeldigheid deur ‘n
literatuurstudie en konsep analise behels, sowel as konstruk- en korrelasie geldigheid deur die
vergelyking van die resultate met beskikbare malingering protokolle en operasionele konstrukte.
Die aangepaste Slick kriteria soos voorgestel deur Aronoff, wat toepaslik is op kroniese pyn,
neurokognitiewe, neurologiese en psigiatriese simptome, was ge-identifiseer as die meeste
gepaste kriterium standaard vir vergelyking.
ONTWERP: Die studieontwerp was ‘n beskrywende analitiese studie wat retrospektief uitgevoer
was deur ‘n ondersoek van verslae van versekeraars. Ingeligte toestemming was verkry van
versekeraars wat die wetlike eienaars van die verslae is. ‘n Gerieflikheidsteekproef van 184 gevalle
met depressie en pyn as hoof simptome was geanaliseer. Sydighede was verminder deur
persoonlike inligting te verwyder en die gebruik van ‘n eweknie evaluasie van 20 ewekansige
getrekte gevalle. Voorlopige resultate dui onbevredigende betroubaarheid aan, eerder as
sydighede.
METODE: Gevalle was ge-evalueer volgends die riglyne van die verskeie outeure van die CAT en
aangepaste Slick kriteria, en was sodanig verder gedefinieer om te verseker dat die studie herhaal
kan word.
RESULTATE: Voorkomsgeldigheid was voldoende, maar verbetering is aanbeveel in terme van
gestandardiseerde instruksie en skaal verdeling. Inhoudsgeldigheid was beduidend in vergelyking
met die wetenskaplike literatuur en die geoperasionaliseerde konstrukte. Konstrukgeldigheid was
bevestig deur die positiewe verhoudings tussen die aangepaste Slick en CAT kriteria. ‘n Sterk
korrelasie was gevind tussen die aangepaste Slick en CAT, maar hierdie moet versigtig geinterpreteer
word aangesien verdere navorsing verlang word.
GEVOLGTREKKING: Aanbevelings vir verdere navorsing sluit in die ondersoek van die
inhoudsgeldigheid met eksperte, kriterium- en voorspellingsgeldigheid, sowel as die
betroubaarheid van die CAT en die gebruik van gespesialiseerde ADL indekse vir uitkenning van
malingering. Aanpassing vir die CAT word ook voorgestel.
|
7 |
Informing Industry End-Users on the Credibility of Model Predictions for Design DecisionsJakob T Hartl (13145352) 25 July 2022 (has links)
<p>Many industrial organizations invest heavily in modeling and simulation (M&S) to support the design process. The primary business motivation for M&S is as a cheaper and faster alternative for obtaining information towards a better understanding of system behavior or to help with decision making. However, M&S predictions are known to be inexact because models and simulations are mathematical approximations of reality. To ensure that models are applicable for their intended use, organizations must collect evidence that the M&S is credible. Verification, validation, and uncertainty quantification (VVUQ) are the established methods for collecting this evidence. Structured frameworks for building credibility in M&S through VVUQ methods exist in the scientific literature but these frameworks and methods are generally not well developed, nor well implemented in industrial environments. The core motivation of this work is to help make existing VVUQ frameworks more suitable for industry.</p>
<p>As part of this objective, this work proposes a new credibility assessment that turns VVUQ results into an intuitive, numerical decision-making metric. This credibility assessment, called the Credibility Index, identifies the important aspects of credibility, extracts the relevant VVUQ results, and converts the results into an overall Credibility Index score (CRED). This CRED score is unique for each specific prediction scenario and serves as an easy-to-digest measure of credibility. The Credibility Index builds upon widely accepted definitions of credibility, well-established VVUQ frameworks, and decision theory.</p>
<p>The Credibility Index has been applied to several prediction scenarios for two publicly available benchmark problems and one Rolls-Royce funded subsystem case; all examples relate to the aerodynamic design of turbine-engine compressors. The results from these studies show how the Credibility Index serves as a decision-making metric, supplements traditional M&S outputs, and guides VVUQ efforts. A product feedback study, involving model end-users in industry, compared the Credibility Index to three other established credibility assessments; the study provides evidence that CRED consistently captures all key aspects of information quality when informing end-users on the credibility of model predictions. Due to the industry partnership, this research already has multiple avenues of practical impact, including implementation of the structured VVUQ and credibility framework in an industrial toolkit and workflow. </p>
|
8 |
Kunskapsbrist eller värderingstvist? : Den romantiska liberalismens frihetsideal i ett urval västerländska länders asylprövning då sexuell läggning eller könsidentitet åberopas som asylskäl. / Is it Rather a Matter of Values? : On the Romantic Liberalism and its Freedom Ideals in a sample of Western Asylum Procedures were Lgbtq+-claims are made.Ezimoha, Stella January 2020 (has links)
Då asylsökande åberopar sexuell läggning eller könsidentitet som asylskäl, är den egna berättelsen inte sällan den enda bevisning som finns att tillgå. Detta innebär att trovärdigheten i den asylsökandes framförande av sin berättelse tillmäts stor vikt. Tidigare forskning har funnit att trovärdighetsbedömningen i västerländska länders asylprövning påverkas av vilken handläggare som hanterar ärendet, och dennas stereotyper av sexuell läggning och könsidentitet. Förekomsten av stereotyper har härletts till kompetens- eller rutinbrist. Exempelvis har det anförts att asylprövande myndigheter och domstolar lider brist på normkritik och nyanserad kunskap i hbtq+-personers olika omständigheter och leverne. Denna studie erbjuder en annan hypotes, med utgångspunkt i etablerad politisk teori och samtida statsvetenskaplig forskning: Att ideologin romantisk liberalism präglar västerländska länders asylprövning. Det finns empiriskt stöd för att människor i västvärlden i allt större utsträckning värdesätter individuell frihet. Tidigare forskning har antagit att detta värdesättande leder till ökad tolerans och välkomnande av ökad mångfald. Ett sådant positivt förhållande ifrågasätts emellertid av flera statsvetare, däribland den svenska statsvetaren Gina Gustavsson. I en avhandling från 2014 presenterar Gustavsson en beskrivning av en romantisk gren inom liberalismen. Denna ideologi framhåller ett obevekligt, provokativt och kreativt uttryck för individens originalitet: både vad avser beskrivningar av vad människan är, och värderande utsagor om hur människan bör vara. En sådan syn, menar Gustavsson, är en förrädisk förståelse för frihet som kan urarta i intolerans, trots att den utges för det motsatta. Med ideologianalys prövas rätts- och myndighetsmaterial från ett urval västerländska länders asylprövning mot en idealtyp av den romantiska liberalismen. Resultatet är att den romantiska liberalismens frihetsideal i flera avseenden kommer till uttryck i urvalet västerländska länders asylprövning. Slutsatsen är att beslutsfattare och utredares upptagenhet av särskilda uttryck för den asylsökandes identitet, kan förstås som en manifestation av den romantiska liberalismens frihetsideal. Detta snarare än som uttryck främst för kompetens- och rutinbrist, såsom tidigare forskning konstaterat. Vidare förs en diskussion kring betydande spänningar mellan den romantiska liberalismen och mänskliga rättigheters universella anspråk. Detta särskilt avseende asylsökandes begränsade möjlighet eller avsikt att leva upp till romantiskt liberala frihetsideal. / As asylum seekers invoke sexual orientation or gender identity as a reason for asylum, their own story is often the only evidence available. This means that the credibility of asylum seeker's presentation of their story, often is given great importance. Previous research shows that credibility assessments in Western countries can differ depending on the sexual orientation and gender identity stereotypes of the case officer who is handling the case. The existence of stereotypes has been related to lack of skills or routine. For example, it is in previous research stated that asylum reviewing authorities and courts suffer from a lack of norm criticism and nuanced knowledge of lgbtq+-persons' different circumstances and living. This study offers another hypothesis, based on established political theory and contemporary political science research: That the ideology romantic liberalism characterizes the asylum procedure in Western countries. There is empirical support for the fact that people in the Western world increasingly value individual freedom. Previous research has assumed that such values leads to increased tolerance and a welcoming of diversity. However, such a positive relationship is questioned by the Swedish political scientist Gina Gustavsson. In Gustavssons’ dissertation from 2014, a description of a romantic branch of liberalism is presented, which elevates a relentless, creative and provocative expression of the individual's originality: both in terms of descriptions of what an individual is, and evaluative statements about what an individual should be. Such a view, Gustavsson says, is a treacherous understanding of freedom that can degenerate into intolerance, even though it is issued to stand for the contrary. With ideology analysis, judicial and governmental material from a sample of Western countries' asylum procedures is tested against an ideal type of romantic liberalism. The results of the analysis show that the ideal of freedom of romanticism, in several respects, can be found in the asylum procedure in a sample of Western countries. The conclusion is that decision makers and investigators' preoccupation with specific expressions of the identity of the asylum seeker can be understood as a manifestation of the freedom ideals in the romantic liberalism. This rather than a lack of skills and routine, as previous research has found. Furthermore, a discussion is held regarding that there is considerable tension between romantic liberalism and the universal claims of human rights. This particularly regarding the asylum seekers' limited ability or intention to live up to the freedom ideals of the romantic liberalism.
|
Page generated in 0.1134 seconds