What Are We Talking About? Natural Language Processing in Organisations
Bibliographic record
Abstract
This symposium is designed to advance research on organizational communication by bringing together leading scholars examining state- of-the-art applications of natural language processing. Language is endemic to almost every aspect of an organization - we talk and write to each other all the time. However, the dominant paradigms for studying social interactions involves indirect measures of communication - for example, by manipulating language in a lab experiment, or by surveying people about their previous interactions. These methods allow researchers to structure their data in advance. But naturally occurring data from communication - the text and speech itself - is unstructured, and presents many common analytical challenges for those who care about the consequences of that communication. The presentations in this symposium demonstrate how that communication can be measured directly. Each presenter considers natural language data from common and difficult conversations throughout an organization. And in each case, natural language processing is used to show that the content of the communication has direct consequences for organizational outcomes. Across different field settings, we show how our analyses can also provide evidence for biases and information gaps that can inform behavioral models of decision-making in an organization. ·Beyond Sentiment: The Value and Measurement of Certainty in Language Author: Matthew Rocklage; Northeastern U. Author: Sharlene He; Concordia U. Author: Derek Rucker; Northwestern Kellogg School of Management Author: Loran F. Nordgren; Northwestern U. ·Back to the Future: A “Lab-in-the-Field” Experiment On Mental Time Travel in Startup Teams Author: Madison Singell; Stanford Graduate School of Business Author: Andrea Freund; Stanford Graduate School of Business Author: Hayagreeva Rao; Stanford U. Author: Margaret A. Neale; Professor emerita Stanford Graduate School of Business ·Conversational receptiveness is contagious and reduces affective polarization Author: Michael Yeomans; Imperial College Business School ·Identifying and predicting the diversity of stereotype change in natural language Author: Tessa Charlesworth; Northwestern Kellogg School of Management Author: Mark HATZENBUEHLER; Harvard U. Author: Mazarin Banaji; Harvard U.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.031 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.004 | 0.010 |
| Scholarly communication | 0.014 | 0.017 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".