Proceedings of the 4th International Workshop on Modeling Social Media
Bibliographic record
Abstract
In our first workshop on Modeling Social Media (MSM 2010 in Toronto, Canada), we explored various different models of social media ranging from user modeling, hypertext models, software engineering models, sociological models and framework models. In our second workshop (MSM 2011 in Boston, USA), we addressed the user interface aspects of modeling social media. In our third workshop (MSM 2012 in Milwaukee, USA), we looked at the collective intelligence in social media, i.e. making sense of the content and context from social media websites such as Facebook, Twitter, Google+ and Foursquare by analyzing tweets, tags, blog posts, likes, posts and check-ins, in order to create a new knowledge and semantic meaning. The goal of this workshop (MSM 2013) is to continue our vibrant discussion on social media mining and modeling with a special focus on recommender systems for social media applications. Hence, the workshop aims to attract and discuss various novel aspects of social media mining, modeling and doing recommendations on top of these data/models. In short, the workshop invites topics such as social media mining methods/techniques, novel approaches to model users or things in social media, frameworks to harvest and/or display social media data and new social media recommender methods/techniques/algorithms or interfaces supporting users for instance in information finding, meta-data application etc. Thus, our goal is to bring together researchers and practitioners from all over the world with diverse backgrounds interested in 1) exploring different perspectives and approaches to mine (complex) and analyse social media data, 2) modeling social media users and 3) building applications such as recommender systems on top of this data/models.
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 | 0.009 | 0.018 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.004 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.008 | 0.008 |
| Open science | 0.004 | 0.005 |
| Research integrity | 0.003 | 0.005 |
| Insufficient payload (model declined to judge) | 0.039 | 0.012 |
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".