Proceedings of the Tenth International Workshop on Natural Language Processing for Social Media
Bibliographic record
Abstract
Happy 10th Anniversary to SocialNLP!It is our great pleasure to welcome you to the Tenth Workshop on Natural Language Processing for Social Media-SocialNLP 2022, associated with NAACL 2022.SocialNLP is an inter-disciplinary area of natural language processing (NLP) and social computing.We hold SocialNLP twice a year: one in the NLP venue, the other in the associated venue such as those for web technology or artificial intelligence.This year the other version has been successfully held in conjunction with TheWebConf 2022 (formerly WWW), and we are very happily looking forward to the NLP version in NAACL 2022.We are very glad that the number of submissions to this year's workshop keeps increasing, and the submissions themselves were still of high quality with the accepted threshold of 3.33 (maximum 5), which again leads to a competitive selection process.We received submissions from Asia, Europe, and the United States.Considering the review process is rigorous and we want to encourage authors to participate in the workshop, we accepted 8 oral papers.These exciting papers include novel and practical topics for researchers working on NLP for social media, such as bias mitigation, domain transfer, and dataset constructed for the newly emerged research problems.We believe they will benefit our research community.On this 10th anniversary, we would like to share our happiness and celebrate the success together with our community members with the special speaker reunion event.Most of our previous invited speakers, including Prof.
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 | 0.011 | 0.016 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.008 | 0.012 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.003 | 0.005 |
| Insufficient payload (model declined to judge) | 0.063 | 0.030 |
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".