Leveraging text mining and network analysis for a semi-automated work order process analytics
Bibliographic record
Abstract
Work order (WO) processing is a basic function of facilities management (FM). WOs are usually captured using computerized maintenance and management systems (CMMS) and contain valuable information about the performance of a building. They provide a very direct pathway to understanding the experiences of different building users and managers. However, given that this knowledge is in the form of unstructured text, the knowledge has remained vastly untapped. There are critical gaps related to the process of handling a WO. Each WO requires the communication of several people to make decisions such as, how urgent the order is, who is responsible for the task, and how much budget should be allocated for dealing with it. Given that the CMMS systems are not inherently designed for streamlining such communications, several challenges may occur during the decision-making processes. For instance, the task might be assigned to the wrong person, or its urgency might be evaluated incorrectly. This research will use the case of the university of Toronto to review key challenges during the process of handling a WO. Next, the research will discuss how text mining, network analysis, and machine learning can help automate WO process analytics. The results show that automating the WO process analytics can significantly improve FM by providing managers with insights about the key pain points and bottlenecks during the everyday management operations.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.006 | 0.006 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.005 |
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".