Abstract
Information forms the basis for all human behavior, including the ubiquitous decision-making that people constantly perform in their every day lives. It is thus the mission of researchers to understand how humans process information to reach decisions. In order to facilitate this task, this work proposes LASSO regularization as a statistical tool to extract decisive words from textual content in order to study the reception of granular expressions in natural language. This differs from the usual use of the LASSO as a predictive model and, instead, yields highly interpretable statistical inferences between the occurrences of words and an outcome variable. Accordingly, the method suggests direct implications for the social sciences: it serves as a statistical procedure for generating domain-specific dictionaries as opposed to frequently employed heuristics. In addition, researchers can now identify text segments and word choices that are statistically decisive to authors or readers and, based on this knowledge, test hypotheses from behavioral research.
Highlights
The power of word choice and linguistic style is undisputed in the social sciences
We evaluate our method with two studies from different domains: (I) we investigate the role of word choice in recommender systems by extracting opinionated terms from usergenerated reviews. (II) We further study the impact on stock markets of the wording in Statistical inferences from natural language financial disclosures
We suggest the following extension to our framework: if desired, one could extend the LASSObased approach with a hierarchical formulation, such that terms are associated with contextspecific polarity score; the resulting caveats are a larger corpora, the challenges from a context-dependent interpretation and the mismatch with the majority of dictionary-based use cases
Summary
The power of word choice and linguistic style is undisputed in the social sciences. Linguistic style provides a means for deception [1, 2]. Likewise, marketing professionals have long understood the value of choosing the right terms when advertising products. The use of technical terms facilitates the success of print advertisements [3]. The use of more positive expressions in user- and marketer-generated content in social media has a clear impact on purchase decisions [4]. In a recent study, [5] manipulate the tone of corporate news in a randomized controlled experiment and find that subjects expect a higher future return from a given firm when reading an article skewed towards positive language
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
