The linguistic correlates of conversational deception: Comparing natural language processing technologies

2010 ◽  
Vol 31 (3) ◽  
pp. 439-462 ◽  
Author(s):  
NICHOLAS D. DURAN ◽  
CHARLES HALL ◽  
PHILIP M. MCCARTHY ◽  
DANIELLE S. MCNAMARA
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Computer Mediated Communication ◽  
Mental States ◽  
Linguistic Features ◽  
Mediated Communication ◽  
Processing Technologies ◽  
Natural Language Processing Tool ◽  
Hidden States

ABSTRACTThe words people use and the way they use them can reveal a great deal about their mental states when they attempt to deceive. The challenge for researchers is how to reliably distinguish the linguistic features that characterize these hidden states. In this study, we use a natural language processing tool called Coh-Metrix to evaluate deceptive and truthful conversations that occur within a context of computer-mediated communication. Coh-Metrix is unique in that it tracks linguistic features based on cognitive and social factors that are hypothesized to influence deception. The results from Coh-Metrix are compared to linguistic features reported in previous independent research, which used a natural language processing tool called Linguistic Inquiry and Word Count. The comparison reveals converging and contrasting alignment for several linguistic features and establishes new insights on deceptive language and its use in conversation.

Machine-learning as a validated tool to characterize individual differences in free recall of naturalistic events.

2021 ◽  
Author(s):  
Xinxu Shen ◽  
Troy Houser ◽  
David Victor Smith ◽  
Vishnu P. Murty
Keyword(s):  
Machine Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Individual Difference ◽  
Language Processing ◽  
Large Scale ◽  
High Reliability ◽  
Difference Analysis ◽  
Universal Sentence ◽  
Natural Language Processing Tool

The use of naturalistic stimuli, such as narrative movies, is gaining popularity in many fields, characterizing memory, affect, and decision-making. Narrative recall paradigms are often used to capture the complexity and richness of memory for naturalistic events. However, scoring narrative recalls is time-consuming and prone to human biases. Here, we show the validity and reliability of using a natural language processing tool, the Universal Sentence Encoder (USE), to automatically score narrative recall. We compared the reliability in scoring made between two independent raters (i.e., hand-scored) and between our automated algorithm and individual raters (i.e., automated) on trial-unique, video clips of magic tricks. Study 1 showed that our automated segmentation approaches yielded high reliability and reflected measures yielded by hand-scoring, and further that the results using USE outperformed another popular natural language processing tool, GloVe. In study two, we tested whether our automated approach remained valid when testing individual’s varying on clinically-relevant dimensions that influence episodic memory, age and anxiety. We found that our automated approach was equally reliable across both age groups and anxiety groups, which shows the efficacy of our approach to assess narrative recall in large-scale individual difference analysis. In sum, these findings suggested that machine learning approaches implementing USE are a promising tool for scoring large-scale narrative recalls and perform individual difference analysis for research using naturalistic stimuli.

New Media for Endangered Languages

2018 ◽  
pp. 509-530
Author(s):  
Laura Buszard-Welcher
Keyword(s):  
Natural Language Processing ◽  
New Media ◽  
Natural Language ◽  
Language Processing ◽  
Good News ◽  
Endangered Languages ◽  
Mediated Communication ◽  
Language Community ◽  
The World ◽  
Electronically Mediated Communication

This chapter presents three technologies essential to enabling any language in the digital domain: language identifiers (ISO 639-3), Unicode (including fonts and keyboards), and the building of corpora to enable natural language processing. Just a few major languages of the world are well-enabled for use with electronically mediated communication. Another few hundred languages are arguably on their way to being well-enabled, if for market reasons alone. For all the remaining languages of the world, inclusion in the digital domain remains a distant possibility, and one that likely requires sustained interest, attention, and resources on the part of the language community itself. The good news is that the same technologies that enable the more widespread languages can also enable the less widespread, and even endangered ones, and bootstrapping is possible for all of them. The examples and resources described in this chapter can serve as inspiration and guidance in getting started.

scholarly journals From SARS to COVID-19: A Bibliometric study on Emerging Infectious Diseases with Natural Language Processing technologies

2020 ◽  
Author(s):  
Yinjun Hu ◽  
Mengmeng Chen ◽  
Qian Wang ◽  
Yue Zhu ◽  
Bei Wang ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
International Collaboration ◽  
Citation Impact ◽  
Policy Decision ◽  
Research Quality ◽  
First Year ◽  
Asian Countries ◽  
Processing Technologies

Abstract [Background] On January 7, 2020, the novel coronavirus named "COVID-19" aroused worldwide concern was identified by Chinese scientists. Many related research works were developed for the emerging, rapidly evolving situation of this epidemic. This study aimed to analyze the research literatures on SARS, MERS and COVID-19 to retrieve important information for virologists, epidemiologist and policy decision makers. [Methods] In this study, we collected data from multi data sources and compared bibliometrics indices among COVID-19, Severe Acute Respiratory Syndrome (SARS), and Middle East Respiratory Syndrome (MERS) up to March 25, 2020. In purpose to extract data in corresponding quantity and scale, the volume of search results will be balance with the limitation of publication years. For further analysis, we extracted 1,480 documents from 1,671 candidates with Natural Language Processing technologies. [Results] In total, 13,945 research literatures of 7 datasets were selected for analysis. Unlike other topics, research passion on epidemic may reach its peak at the first year the outbreak happens. The document type distribution of SARS, MERS and COVID-19 are nearly the same (less than 6 point difference for each type), however, there were notable growth in the research qualities during these three epidemics (3.68, 6.63 and 11.35 for Field-Weighted Citation Impact scores). Asian countries has less international collaboration (less than 35.1\%) than the Occident (more than 49.5\%), which should be noticed as same as research itself. [Conclusions] We found that research passion on epidemics may always reach its peak at the first year after outburst, however, the peak of research on MERS appeared at the third year because of its outburst of reproduction in 2015. For the research quality, although we did better in research qualities than before especially on COVID-19, research on epidemics not started from our own country should not be looked down. Another important effective strategy for enhancing epidemic prevention for China and other Asian countries is to continue strengthening international collaboration.

Sign in / Sign up

Export Citation Format

Share Document