The Development and Psychometric Properties of LIWC2015

By James W. Pennebaker, Ryan L. Boyd, Kayla Jordan, Kate G. Blackburn. 2015

2,557 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/26588cb2a9902599872b6fe7692fc1ab7c459207

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

The fake news game: actively inoculating against the risk of misinformation (2019, methodology): “Lastly, we conducted a sentiment analysis on the open-ended responses with the Linguistic Inquiry and Word Count dictionary (Pennebaker et al. 2015), to see if the active evaluation of (counter)-arguments elicited affective responses (H4).”
dEFEND: Explainable Fake News Detection (2019, background): “For feature extraction methods such as RST and LIWC, we feed them into different learning algorithms and choose the one that achieves the best performance.”
Does It Capture STEL? A Modular, Similarity-based Linguistic Style Evaluation Framework (2021, methodology): “We use LIWC 2015 (Pennebaker et al., 2015) for (a) LIWC similarity by taking the cosine similarity between the complete LIWC frequency vectors, (b) LIWC (style) similarity by taking the cosine similarity between the 8 dimensional binary LIWC style vectors (1 if a word of the category is present in…”
Demographics of News Sharing in the U.S. Twittersphere (2017, methodology): “Its latest version, LIWC 2015 (used in this work), defines about 90 linguistic categories and classifies more than 6,400 words into those categories [32].”
Forecasting the onset and course of mental illness with Twitter data (2016, background): “, food words, familial terms, profanity) as additional predictors (36).”
Natural language processing in mental health applications using non-clinical texts† (2017, methodology): “For example, Kramer et al. (2014)’s study that manipulated Facebook News Feed ﬁlters (described in Section 3.2) used emotion terms from LIWC.”
Identity Deception Detection (2017, background): “Semantic LIWC These features include the 74 semantic classes present in the LIWC lexicon 2015 (Pennebaker et al., 2015).”
Effects of an Advancing Tenure on CEO Cognitive Complexity (2020, methodology): “…Word Count (LIWC) software, which was developed and extensively validated by Pennebaker and colleagues (Duriau et al. 2007, Pennebaker et al. 2007, Pennebaker et al. 2015), and the dictionaries developed by Loughran and McDonald (2011), specifically for analyzing textual material in a business…”
Automatic Detection of Fake News (2017, methodology): “We construct a punctuation feature set consisting of eleven types of punc-tuation derived from the Linguistic Inquiry and Word Count software (LIWC, Version 1.3.1 2015) (Pennebaker et al., 2015).”
The Illusion of Control: Placebo Effects of Control Settings (2018, unknown): “Sentiment was calculated using LIWC [45].”
Automated Fact Checking: Task Formulations, Methods and Future Directions (2018, methodology): “Analysis of the model identifies a number of word classes of the LIWC lexicon which pertain only to the deceptive texts.”
Mining Big Data in Education: Affordances and Challenges (2020, methodology): “Similarly, the Linguistic Inquiry and Word Count tool (Pennebaker et al., 2015) measures psychological constructs including confidence, leadership, authenticity, and emotional tone.”
Exploring the Role of Grammar and Word Choice in Bias Toward African American English (AAE) in Hate Speech Classification (2022, background): “The LIWC2007 dictionary was created with English text samples sourced from a variety of studies from the United States, England, Canada, New Zealand, and Australia [28].”
How Concrete Language Shapes Customer Satisfaction (2020, background): “…for other major language features that have been extensively linked to psychological phenomena, we include the psychological process dictionaries from Linguistic Inquiry and Word Count (LIWC; cognition, emotion, sociality, perception, motivation, time, and formality; Pennebaker et al. 2015).”
Comprehensive stereotype content dictionaries using a semi‐automated method (2020, methodology): “For example, many of the LIWC dictionaries used up to 8 judges across several stages in order to manually expand the word lists (Pennebaker et al., 2015).”