Problem Event Extraction to Develop Causal Loop Representation from Texts
| Autor: | Narongdech Keeratipranon, Chaveevan Pechsiri, Intaka Piriyakul |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Series (mathematics)
Computer science business.industry Causal loop diagram Representation (systemics) 020207 software engineering Verb phrase 02 engineering and technology computer.software_genre Set (abstract data type) Expression (architecture) Similarity (psychology) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business computer Natural language processing Event (probability theory) |
| Zdroj: | 2019 5th International Conference on Science in Information Technology (ICSITech). |
| Popis: | This research aims to extract consequent problem events as a cause-effect concept pair series, from teen-drug addiction web-boards. The extracted consequent problem events benefit for a problem analysis in a solving system through a Causal Loop representation. The research has three problems; how to determine a causative/effect event concept based on a verb phrase expression with an overlap problem between causative-verb concept set and effect-verb concept set, how to determine cause-effect concept pair series from several verb phrases, and how to develop a Causal Loop representation from the extracted cause-effect concept pair series. Therefore, we apply an event rate to solve the overlap problem. We then propose using N-WordCo to determine the cause-effect concept pair series and also use a similarity score to develop the Causal Loop representation. The research results provide a high precision of the problem event extraction from the documents. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|