A THREE-STEP SPATIAL-TEMPORAL-SEMANTIC CLUSTERING METHOD FOR HUMAN ACTIVITY PATTERN ANALYSIS
Bibliographic record
Abstract
Abstract. How people move in cities and what they do in various locations at different times form human activity patterns. Human activity pattern plays a key role in in urban planning, traffic forecasting, public health and safety, emergency response, friend recommendation, and so on. Therefore, scholars from different fields, such as social science, geography, transportation, physics and computer science, have made great efforts in modelling and analysing human activity patterns or human mobility patterns. One of the essential tasks in such studies is to find the locations or places where individuals stay to perform some kind of activities before further activity pattern analysis. In the era of Big Data, the emerging of social media along with wearable devices enables human activity data to be collected more easily and efficiently. Furthermore, the dimension of the accessible human activity data has been extended from two to three (space or space-time) to four dimensions (space, time and semantics). More specifically, not only a location and time that people stay and spend are collected, but also what people “say” for in a location at a time can be obtained. The characteristics of these datasets shed new light on the analysis of human mobility, where some of new methodologies should be accordingly developed to handle them. Traditional methods such as neural networks, statistics and clustering have been applied to study human activity patterns using geosocial media data. Among them, clustering methods have been widely used to analyse spatiotemporal patterns. However, to our best knowledge, few of clustering algorithms are specifically developed for handling the datasets that contain spatial, temporal and semantic aspects all together. In this work, we propose a three-step human activity clustering method based on space, time and semantics to fill this gap. One-year Twitter data, posted in Toronto, Canada, is used to test the clustering-based method. The results show that the approximate 55% spatiotemporal clusters distributed in different locations can be eventually grouped as the same type of clusters with consideration of semantic aspect.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.007 | 0.007 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".