Identification of Occupant Dissatisfaction Factors in Newly Constructed Apartments: Text Mining and Semantic Network Analysis
Bibliographic record
Abstract
With apartment buildings representing a rapidly growing share of the residential market in South Korea, the effect of construction defects throughout the life cycle of construction projects, and particularly during the occupancy stage, has emerged as a significant social issue that may ultimately lead to an increase in defect disputes between new occupants and general contractors. An important step toward mitigating the likelihood of these defect disputes is to identify and address the factors that give rise to occupant dissatisfaction during the defect repair process. However, a reliable method by which to identify these factors has yet to be developed. In this respect, the main objective of the research presented in this paper is to develop a method for identifying occupant dissatisfaction factors in the construction defect repair stage. The developed method comprises the following procedures: (i) text pre-processing, which involves data cleaning, normalization, tokenization, morphological analysis, and removal of stopwords; (ii) term frequency–inverse document frequency for keyword extraction; and (iii) semantic network analysis to recognize relationships between words. The method was implemented using a dataset of 12,874 comments in Korean text format obtained from apartment building occupants. Based on the processing and analysis of this dataset, the occupant dissatisfaction factors were found to be: (i) inaccurate and inadequate repair work (represented by such keywords as “Repair”, “Visit”, and “Accuracy”); (ii) failure to keep promises (e.g., “Fulfillment”, “Promise”, and “Change”); and (iii) unprofessional conduct on the part of representatives in the repair service center (e.g., “Response”, “Attitude”, and “Receipt”).
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) | 0.000 | 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".