Data analysis and coding

A Journal of Applied Psychology study builds 17 word dictionaries that score essays and interview answers, predicting selection with small subgroup gaps.

Audit AI-generated analysis with a synthetic CSV, duplicate and missing-value checks, tested Python code and an exact answer you can reproduce.

Audit AI-written analysis code with hand-checkable examples, protected raw data, statistical review, and a clean rerun of your research outputs.

Lookahead bias in LLM-based social science, hidden leakage inside autonomous AI scientists, AI that resolves open Erdős problems, and what ChatGPT did to firm values.

Louis Luangkesorn walks through an analytics project lifecycle with generative AI and shows where foundation models fail.

Claude Code, Codex and Gemini CLI can run a whole analysis from raw data to figure. Here is how to set up the project so the result is reproducible.

A PNAS reanalysis shows a headline result on LLM-driven research productivity can be reproduced with random, inverted and pre-ChatGPT placebo treatments — plus AI agents that can't yet reproduce their own field's papers, platform AI policies that drive creators away, and LLM-simulated bank runs.

Consumer psychologists debate AI-assisted grounded theory, management scholars audit 353 computational-linguistics papers, and legal researchers argue that nobody is independently benchmarking the AI tools already in professional use.

A new PNAS study built autonomous AI analysts and turned them loose on fixed datasets. They reproduced the dispersion of human many-analyst studies — and swapping the analyst's persona shifted the results, even among methodologically sound runs.

A new ISR study shows why feeding AI-generated variables straight into your regressions biases the results — plus a deep-learning ECG biomarker, agentic GenAI in operations, and meta-learning for consumer preferences.

On April 5, we hosted the second day of the workshop. Please also take a look of our github page for slides, readings, learning materials... http://github.com/lanceyuu/osloworkshop Morning session No code programming for research RAG Afternoon session Data analysis using GPT, Claude, Gemini Visualization using LLMs and colab Fine tuning a LLM using EASY DATASET Synthetic data

Imagine you're trying to organize thousands of comments about a product into main themes or topics. Traditionally, researchers either had to read through everything manually (time-consuming and expensive) or use older computer programs that often missed important context. A new preprint from OSF shows that modern AI systems like GPT-4, Claude, and Gemini can do this job effectively, especially with short pieces of text. The researchers conducted two interesting experiments: S

A new study published in the Proceedings of the National Academy of Sciences finds that the artificial intelligence chatbot GPT is an effective tool for analyzing psychological constructs in text across multiple languages. Researchers from Stanford University, Princeton University and New York University tested GPT's ability to detect sentiment, emotions, offensiveness and moral foundations in texts written in 12 different languages. They found that GPT performed significantl

Build a small ScrapeGraphAI extraction pilot, follow maintained examples, inspect records against source pages and document the full data path.

Plan AI-assisted web extraction with a sampling rule, explicit schema, source log and validation checks. Includes the original tutorial recordings.

Jan Ole Krugmann & Jochen Hartmann Abstract In the rapidly advancing age of Generative AI, Large Language Models (LLMs) such as ChatGPT stand at the forefront of disrupting marketing practice and research. This paper presents a comprehensive exploration of LLMs’ proficiency in sentiment analysis, a core task in marketing research for understanding consumer emotions, opinions, and perceptions. We benchmark the performance of three state-of-the-art LLMs, i.e., GPT-3.5, GPT-4, a

Identify topics with AI using source-linked labels, a reviewed codebook, held-out examples and frequencies calculated from checked assignments.

Fabrizio Gilardi https://orcid.org/0000-0002-0635-3048 gilardi@ipz.uzh.ch, Meysam Alizadeh https://orcid.org/0000-0001-6696-6471, and Maël Kubli https://orcid.org/0000-0002-5592-9648 Authors Info & Affiliations Edited by Mary Waters, Harvard University, Cambridge, MA; received March 27, 2023; accepted June 2, 2023 July 18, 2023 120 (30) e2305016120 https://doi.org/10.1073/pnas.2305016120 Abstract Many NLP applications require manual text annotations for a variety of tasks, no

Gaël Le Mens https://orcid.org/0000-0003-4800-0598 gael.le-mens@upf.edu, Balázs Kovács https://orcid.org/0000-0001-6916-6357, Michael T. Hannan https://orcid.org/0000-0002-7664-9565, and Guillem Pros https://orcid.org/0009-0009-9937-4902 Authors Info & Affiliations Edited by Kenneth Wachter, University of California, Berkeley, CA; received June 3, 2023; accepted October 13, 2023 November 30, 2023 120 (49) e2309350120 https://doi.org/10.1073/pnas.2309350120 We use GPT-4 to cre

Watch a curated Data Science Dojo webinar, practise with a worked CSV example and check AI-generated calculations against reproducible results.