Use of a text mining method for classifying citizen report data and analyzing the occurrence trend of local problems
Bibliographic record
Abstract
An important task of any municipality is the maintenance and improvement of the street-related living environment and traffic safety for citizens. For this, their department of street maintenance is expected to efficiently perform the maintenance and inspection of streets according to priority with limited human and budgetary resources. Recently, municipalities in various countries are adopting “the citizen report system,” which is a system of reporting problems of streets, such as damaged streets, by citizens to their municipality, for citizens to perform part of street maintenance and inspection. It is possible that the data obtained by municipalities through the citizen report system can be utilized not only for early problem detection but also for prioritizing administrative measures by using it for analyzing the occurrence trend of problems. Problems reported by citizens, however, are classified by different methods from municipality to municipality, and thus the collection and comparative analysis of such data across municipalities is difficult. This study presents a method of commonly classifying such data, regardless of different classification standards, by analyzing the contents of citizen reports by using text mining. We then analyze the relationship between the trend of citizen reports and the occurrence trend of problems concerning the living environment and traffic safety, using the citizen report data of three large municipalities classified by this method, and infer the occurrence trend of problems. This study has confirmed that citizen report data possibly contributes to municipalities’ prioritization of the maintenance and improvement of the living environment and traffic safety.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.010 | 0.008 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".