To find out how users' social media be haviour and language are related to their ethical practices, the paper investigates ap plying Schwartz' psycholinguistic model of societal sentiment to social media text. The analysis is based on corpora collected from user essays as well as social media (Facebook and Twitter). Several experi ments were carried out on the corpora to classify the ethical values of users, incor porating Linguistic Inquiry Word Count analysis, n-grams, topic models, psycho-linguistic lexica, speech-acts, and non-linguistic information, while applying a range of machine learners (Support Vector Machines, Logistic Regression, and Ran dom Forests) to identify the best linguistic and non-linguistic features for automatic classification of values and ethics.
展开▼