Communication accommodation is a phenomenon in social in-teractions in which people adjust their language to that of theirinterlocutor. A component of communication accommodationis research on power and dominance relations which suggestslanguage use is dependent on power position. There are differ-ent linguistic markers which imply power standing of people.For example, when high power individuals interact with peoplein low power positions, the language of the interaction tends tofollow the language of the high power individuals. While pre-vious studies have mostly focused on the word-level features,we show that not only people in low power mirror word usageof people in high power, but they also adjust their syntacticstructures to those in high power. Notably, we apply a compu-tational tool on two corpora and show that individuals in lowpower align their syntactic structures to those in high powerwhile people in high power do not.

Technological innovations have become a key driver of societal advancements. Nowhere is this more evident than in the field of machine learning (ML), which has developed algorithmic models that shape our decisions, behaviors, and outcomes. These tools have widespread use, in part, because they can synthesize massive amounts of data to make seemingly objective recommendations. Yet, in the past few years, the ML community has been drawing attention to the need for caution when interpreting and using these models. This is because these models are created by humans, from data generated by humans, whose psychology allows for various biases that impact how the models are developed, trained, tested, and interpreted. As psychologists, we thus face a fork in the road: Down the first path, we can continue to use these models without examining and addressing these critical flaws and rely on computer scientists to try to mitigate them. Down the second path, we can turn our expertise in bias toward this growing field, collaborating with computer scientists to reduce the models' deleterious outcomes. This article serves to light the way down the second path by identifying how extant psychological research can help examine and curtail bias in ML models.

Analysis of language provides important insights into the un-derlying psychological properties of individuals and groups.While the majority of language analysis work in psychologyhas focused on semantics, psychological information is en-coded not just in what people say, but how they say it. Inthe current work, we propose Conversation Level Syntax Simi-larity Metric-Group Representations (CASSIM-GR). This toolbuilds generalized representations of syntactic structures ofdocuments, thus allowing researchers to distinguish betweenpeople and groups based on syntactic differences. CASSIM-GR builds off of Conversation Level Syntax Similarity Metricby applying spectral clustering to syntactic similarity matricesand calculating the center of each cluster of documents. Thisresulting cluster centroid then represents the syntactical struc-ture of the group of documents. To examine the effectivenessof CASSIM-GR, we conduct three experiments across threeunique corpora. In each experiment, we calculate the cluster-ing accuracy and compare our proposed technique to a bag-of-words approach. Our results provide evidence for the ef-fectiveness of CASSIM-GR and demonstrate that combiningsyntactic similarity and tf-idf semantic information improvesthe total accuracy of group classification.

People’s beliefs about what is morally right and wrong vary widely between individuals, contexts, and cultures;however it is thought that they are governed by core latent constructs. While there is evidence that these constructs are reflectedin natural language, this requires further testing. We demonstrate that the structure of moral values in natural discourse can bemodeled by applying factor analyses to distributed representations of morally relevant terms learned by a neural network. Wefirst demonstrate that robust latent constructs can be estimated from the covariance of distributed representations of constructexemplars. We then test whether the factor structure proposed by Moral Foundations Theory (MFT) is reflected in naturallanguage. Finally, we conduct a bottom-up investigation of the structure of moral values in natural language using free-responses reported by participants. Ultimately, we find evidence that the representation of moral values in natural languagepartially corresponds to MFT.