EXPLORING WAYS TO VISUALIZE NEWS OVER GEOGRAPHICAL MAPS
Bibliographic record
Abstract
Online news sites are some of the most useful and popular information retrieval systems in use today. Thousands of articles in different languages and on a variety of subjects are posted every day and updated every hour. Most articles are uninteresting and unimportant to a particular individual, and individuals may not want to review entire websites for stories of interest. Systems have been developed that provide summaries from online news websites but finding a means to rapidly scan stories of potential interest remains an open problem. In this thesis, we introduce a novel visualization system that uses geographical location combined with image collages and tag clouds to provide a tool for rapidly reviewing news stories. Tag clouds are arrangements of tags with the most important tags allocated a bigger font size or otherwise more prominent visual properties; and image collages provide a compact, effective and attractive representation for photos on one page. Bringing these media representations together over a geographic map offers a new style of interaction for online news browsing.\nThe usability of our application was evaluated with two user studies. We aimed to determine how best to configure our visualization to communicate more information in less time to users than traditional feed-based news aggregators. We were particularly interested in knowing whether users interpret text/image size and placement as indications of a news item’s prominence. We also wanted to establish whether users understand the semantic relationship between zoom level on the map and the regional relevance (municipal, provincial, national) of news items displayed at that zoom level. The results of user feedback and data analysis (e.g., eye tracking logs) were examined to improve the usability of the system. Data analysis from the second user study suggests that, in general, the system is highly effective in helping users achieve an immediate and effortless bird’s-eye-view of news summaries within a large geographic region. However, users had varying opinions about the level of detail in the user interface (e.g., the number of images).
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.002 |
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".