TransSentLog: Interpretable Anomaly Detection Using Transformer and Sentiment Analysis on Individual Log Event
Event logs play a crucial role in monitoring the status of IT systems. These logs contain text that describes how a system operates using natural language, which can be associated with sentiment polarity. When a system is functioning correctly, event logs generally convey positive sentiment. However...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10237208/ |
| _version_ | 1797688521606037504 |
|---|---|
| author | Tuan-Anh Pham Jong-Hoon Lee |
| author_facet | Tuan-Anh Pham Jong-Hoon Lee |
| author_sort | Tuan-Anh Pham |
| collection | DOAJ |
| description | Event logs play a crucial role in monitoring the status of IT systems. These logs contain text that describes how a system operates using natural language, which can be associated with sentiment polarity. When a system is functioning correctly, event logs generally convey positive sentiment. However, if unexpected behaviors like errors or failures occur, negative sentiment can be detected. In order to identify anomalies in individual log messages without the need for log parsing, we propose TranSentLog. This method combines Transformer and sentiment analysis, leveraging the sentiment polarity of event logs. To gain a better understanding of the model predictions, we employ Integrated Gradients, an attribution method that extracts important features from the model inputs. Through extensive experimentation on public system log datasets, we demonstrate that our proposed method overcomes the limitations of existing approaches and achieves F1 scores of 99.73% on trained datasets and 94.99% on untrained datasets. |
| first_indexed | 2024-03-12T01:32:06Z |
| format | Article |
| id | doaj.art-4831f4931d3f42139f740c4954394ac5 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T01:32:06Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4831f4931d3f42139f740c4954394ac52023-09-11T23:00:57ZengIEEEIEEE Access2169-35362023-01-0111962729628210.1109/ACCESS.2023.331114610237208TransSentLog: Interpretable Anomaly Detection Using Transformer and Sentiment Analysis on Individual Log EventTuan-Anh Pham0https://orcid.org/0000-0001-5049-529XJong-Hoon Lee1https://orcid.org/0000-0002-7059-3126Department of AI Laboratory, MOADATA, Global Convergence Center, Seongnam-si, South KoreaDepartment of AI Laboratory, MOADATA, Global Convergence Center, Seongnam-si, South KoreaEvent logs play a crucial role in monitoring the status of IT systems. These logs contain text that describes how a system operates using natural language, which can be associated with sentiment polarity. When a system is functioning correctly, event logs generally convey positive sentiment. However, if unexpected behaviors like errors or failures occur, negative sentiment can be detected. In order to identify anomalies in individual log messages without the need for log parsing, we propose TranSentLog. This method combines Transformer and sentiment analysis, leveraging the sentiment polarity of event logs. To gain a better understanding of the model predictions, we employ Integrated Gradients, an attribution method that extracts important features from the model inputs. Through extensive experimentation on public system log datasets, we demonstrate that our proposed method overcomes the limitations of existing approaches and achieves F1 scores of 99.73% on trained datasets and 94.99% on untrained datasets.https://ieeexplore.ieee.org/document/10237208/Log anomaly detectiontransformersentiment analysissystem logintegrated gradients |
| spellingShingle | Tuan-Anh Pham Jong-Hoon Lee TransSentLog: Interpretable Anomaly Detection Using Transformer and Sentiment Analysis on Individual Log Event IEEE Access Log anomaly detection transformer sentiment analysis system log integrated gradients |
| title | TransSentLog: Interpretable Anomaly Detection Using Transformer and Sentiment Analysis on Individual Log Event |
| title_full | TransSentLog: Interpretable Anomaly Detection Using Transformer and Sentiment Analysis on Individual Log Event |
| title_fullStr | TransSentLog: Interpretable Anomaly Detection Using Transformer and Sentiment Analysis on Individual Log Event |
| title_full_unstemmed | TransSentLog: Interpretable Anomaly Detection Using Transformer and Sentiment Analysis on Individual Log Event |
| title_short | TransSentLog: Interpretable Anomaly Detection Using Transformer and Sentiment Analysis on Individual Log Event |
| title_sort | transsentlog interpretable anomaly detection using transformer and sentiment analysis on individual log event |
| topic | Log anomaly detection transformer sentiment analysis system log integrated gradients |
| url | https://ieeexplore.ieee.org/document/10237208/ |
| work_keys_str_mv | AT tuananhpham transsentloginterpretableanomalydetectionusingtransformerandsentimentanalysisonindividuallogevent AT jonghoonlee transsentloginterpretableanomalydetectionusingtransformerandsentimentanalysisonindividuallogevent |