The Experts below are selected from a list of 102 Experts worldwide ranked by ideXlab platform
Chienlung Chan - One of the best experts on this subject based on the ideXlab platform.
-
mining association language patterns using a distributional semantic model for Negative Life Event classification
Journal of Biomedical Informatics, 2011Co-Authors: Liangchih Yu, Chienlung ChanAbstract:Purpose: Negative Life Events, such as the death of a family member, an argument with a spouse or the loss of a job, play an important role in triggering depressive episodes. Therefore, it is worthwhile to develop psychiatric services that can automatically identify such Events. This study describes the use of association language patterns, i.e., meaningful combinations of words (e.g., ), as features to classify sentences with Negative Life Events into predefined categories (e.g., Family, Love, Work). Methods: This study proposes a framework that combines a supervised data mining algorithm and an unsupervised distributional semantic model to discover association language patterns. The data mining algorithm, called association rule mining, was used to generate a set of seed patterns by incrementally associating frequently co-occurring words from a small corpus of sentences labeled with Negative Life Events. The distributional semantic model was then used to discover more patterns similar to the seed patterns from a large, unlabeled web corpus. Results: The experimental results showed that association language patterns were significant features for Negative Life Event classification. Additionally, the unsupervised distributional semantic model was not only able to improve the level of performance but also to reduce the reliance of the classification process on the availability of a large, labeled corpus.
-
mining association language patterns for Negative Life Event classification
Meeting of the Association for Computational Linguistics, 2009Co-Authors: Liangchih Yu, Chienlung Chan, Chunghsien WuAbstract:Negative Life Events, such as death of a family member, argument with a spouse and loss of a job, play an important role in triggering depressive episodes. Therefore, it is worth to develop psychiatric services that can automatically identify such Events. In this paper, we propose the use of association language patterns, i.e., meaningful combinations of words (e.g., ), as features to classify sentences with Negative Life Events into predefined categories (e.g., Family, Love, Work). The language patterns are discovered using a data mining algorithm, called association pattern mining, by incrementally associating frequently co-occurred words in the sentences annotated with Negative Life Events. The discovered patterns are then combined with single words to train classifiers. Experimental results show that association language patterns are significant features, thus yielding better performance than the baseline system using single words alone.
Liangchih Yu - One of the best experts on this subject based on the ideXlab platform.
-
mining association language patterns using a distributional semantic model for Negative Life Event classification
Journal of Biomedical Informatics, 2011Co-Authors: Liangchih Yu, Chienlung ChanAbstract:Purpose: Negative Life Events, such as the death of a family member, an argument with a spouse or the loss of a job, play an important role in triggering depressive episodes. Therefore, it is worthwhile to develop psychiatric services that can automatically identify such Events. This study describes the use of association language patterns, i.e., meaningful combinations of words (e.g., ), as features to classify sentences with Negative Life Events into predefined categories (e.g., Family, Love, Work). Methods: This study proposes a framework that combines a supervised data mining algorithm and an unsupervised distributional semantic model to discover association language patterns. The data mining algorithm, called association rule mining, was used to generate a set of seed patterns by incrementally associating frequently co-occurring words from a small corpus of sentences labeled with Negative Life Events. The distributional semantic model was then used to discover more patterns similar to the seed patterns from a large, unlabeled web corpus. Results: The experimental results showed that association language patterns were significant features for Negative Life Event classification. Additionally, the unsupervised distributional semantic model was not only able to improve the level of performance but also to reduce the reliance of the classification process on the availability of a large, labeled corpus.
-
mining association language patterns for Negative Life Event classification
Meeting of the Association for Computational Linguistics, 2009Co-Authors: Liangchih Yu, Chienlung Chan, Chunghsien WuAbstract:Negative Life Events, such as death of a family member, argument with a spouse and loss of a job, play an important role in triggering depressive episodes. Therefore, it is worth to develop psychiatric services that can automatically identify such Events. In this paper, we propose the use of association language patterns, i.e., meaningful combinations of words (e.g., ), as features to classify sentences with Negative Life Events into predefined categories (e.g., Family, Love, Work). The language patterns are discovered using a data mining algorithm, called association pattern mining, by incrementally associating frequently co-occurred words in the sentences annotated with Negative Life Events. The discovered patterns are then combined with single words to train classifiers. Experimental results show that association language patterns are significant features, thus yielding better performance than the baseline system using single words alone.
Chunghsien Wu - One of the best experts on this subject based on the ideXlab platform.
-
mining association language patterns for Negative Life Event classification
Meeting of the Association for Computational Linguistics, 2009Co-Authors: Liangchih Yu, Chienlung Chan, Chunghsien WuAbstract:Negative Life Events, such as death of a family member, argument with a spouse and loss of a job, play an important role in triggering depressive episodes. Therefore, it is worth to develop psychiatric services that can automatically identify such Events. In this paper, we propose the use of association language patterns, i.e., meaningful combinations of words (e.g., ), as features to classify sentences with Negative Life Events into predefined categories (e.g., Family, Love, Work). The language patterns are discovered using a data mining algorithm, called association pattern mining, by incrementally associating frequently co-occurred words in the sentences annotated with Negative Life Events. The discovered patterns are then combined with single words to train classifiers. Experimental results show that association language patterns are significant features, thus yielding better performance than the baseline system using single words alone.
Zhao Chun - One of the best experts on this subject based on the ideXlab platform.
-
clinical research on Negative Life Event and cell immunity of breast cancer
Cancer Research and Clinic, 2002Co-Authors: Zhao ChunAbstract:Objective:To discuss the relationship among breast cancer,Negative Life Event,cell immunity,lymphatic metastasis and histological kind.Methods:Choose 115 cases of patients who are with breast cancer diagnosed by pathology and cytology and 115 cases of galactophore benign sick and cured at our hospital during the period of 1998 to 2000.The patients are grouped and compared in accordance with the principle of same sex,same occupation,similar educational attainments and living custom and age.The comparison and investigation are carried out in accordance with the Life,work,study,sociality and others published at Life Event (LES) compiled by Yang Desheng.Meanwhile the immunity function of cell is tested.Results: 1. The total score of Negative Life Event in the group of breast cancer is higher than that of control group remarkably ( P 0.001). 2. CD 3 (total T cell) in the group of breast cancer dropped remarkably. The difference between the two groups is obvious ( P 0.001).Nevertheless CD 4 (auxiliary T cell),CD 8 (inhibitory T cell),the ratio between CD 4 and CD 8 and NK cell in the two groups have no obvious difference ( P 0.05). 3.It appears positive relationship between transfer quantity of lymphatic metastasis and the point value of Negative Life Event. 4.The immunity index of cell at different breast cancers exists difference but has no relationship with the point value of Negative Life Event ( P 0.05).Conclusion:The occurrence of breast cancer has close relationship with Negative Life Event;Negative Life Event has relationship with the drop of total T cell and has no relationship with the percent of other cell gene;Negative Life Event has certain effect to lymphatic metastasis of breast cancer;the immunity index of cell at different breast cancers exists difference.
X Lu - One of the best experts on this subject based on the ideXlab platform.
-
relationship among breast cancer and Negative Life Event and cell immunity
National Medical Journal of China, 2002Co-Authors: C Zhao, Q Fang, X LuAbstract:Objective To investigate the relationship among breast cancer and Negative Life Event and cell immunity. Methods A questionnaire survey using the Life Event by YANG Desen to investigate the family Life problems, work problems, and social and other problems was conducted among 115 patients with breast cancer diagnosed by pathology and cytology and 115 gender, age, profession, education, and Life habit-matched patients with benign breast diseases as controls. Fasting blood was drawn from all patients. Fluorescent-labeled bodies were added. Flow cytometry was made to count the immunocytes. Results The Negative Life Event rate was 87% in the breast cancer group, higher than that in the control group (55%, P0.01). The rate of family problems in the breast cancer group was 63%, higher than that in the control group (40%). The total score of Negative Events was 31.5±9.7 in the breast cancer group , higher than that in the control group (17.3±5.6, P0.01).The percentage of CD 3 (total T cell) in the breast cancer group was 58.8±12.2%, significantly lower than that in the control group (63.9±9.9%, P0.01). There was no difference in the percentages of CD 4, CD 8, CD 4/CD 8, and the percentage of natural killer cells (NK) between the two groups. Conclusion Breast cancer is closely correlated with Negative Life Events, especially family problems concerning marriage and children. The Negative Life Events are related to the decrease of total T cells, and unrelated to the percentages of other cells.
