An ontology-based Social Network Analysis prototype
Bibliographic record
Abstract
Many challenges are being faced when attempting to perform meaningful Social Network Analysis (SNA) on covert networks for intelligence purposes. First, data about covert networks are, by definition, difficult to obtain. Information about those networks is well guarded and, in general, not directly accessible. Consequently, intelligence analysts must build their situational awareness based on an overabundance of indirect information and sources which lead to cluttered heterogeneous models of social networks. This challenge actually results in a second concern in SNA, the imperative to manage very large graphs, which leads to the need to sample or select subsets of the overall data set. Finally, in current systems, analyses of social networks seem to be conducted regardless of the intelligence issue being faced or the data context. This facet is critical in order to ensure that the data lying beneath the analysis are actually truly indicators of the intelligence issue being tackled. This paper first describes the SNA capability targeted along with its challenges. Subsequently, explanations and rationales are provided to highlight the critical roles played by ontologies with respect to the challenges described above. In the current prototype, ontologies are being used with respect to four essential aspects of the SNA capability: to automatically identify and extract the social network data of interest; to organize and correlate these social network data based on the context, to create a filter in order to prune only portions of the social network data; and to select appropriate SNA algorithms corresponding to the intelligence issue being faced. Finally, this paper discusses preliminary results from the implementation of these aspects.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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 teacher head, 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".