Subjects: Psychology >> Applied Psychology Subjects: Computer Science >> Computer Application Technology submitted time 2024-02-29
Abstract： Objective With the development of network big data and machine learning, more and more studies starting to combine text analysis and machine learning algorithms to predict individual satisfaction. In the studies focused on building life satisfaction prediction models, it is often difficult to obtain large amounts of valid and labeled data. This study aims at solving this problem using data augmentation and optimizing the prediction model of life satisfaction. Method Using 357 life status descriptions annotated by self-rating life satisfaction scale scores as original text data. After preprocessing using DLUT-Emotionontology, EAD and back-translation method was applied and the prediction model was built using traditional machine learning algorithms. Results Results showed that (1) the prediction accuracy was largely enhanced after using the adapted version of DLUT-Emotionontology; (2) only linear regression model was enhanced after data augmentation; (3) rigid regression model showed the greatest prediction accuracy when trained by original data (r = 0.4131). Conclusion The improvement of feature extraction accuracy can optimize the current life satisfaction prediction model, but the text data augmentation methods, such as back translation and EDA may not be applicable for the life satisfaction prediction model based on word frequency.
Peer Review Status:
Awaiting Review
Subjects: Medicine, Pharmacy >> Preclinical Medicine submitted time 2017-12-21 Cooperative journals: 《南方医科大学学报》
Abstract： Objective To detect the expressions of IL-17, IL-23, IL–22 and IL–11 in the intestinal mucosa of patients with ulcerative colitis (UC) and analyze their prognostic values. Methods Forty patients with active UC, 15 with UC in remission and 15 healthy subjects were examined for the expressions and distribution of IL-17, IL-23, IL-22, and IL-11 in the colorectal mucosausing immunohistochemistry. We further collected the data from 40 patients with routine therapy and regular follow-up and compared the expressions of those cytokines according to the condition of mucosal healing. Results The expressions of cytokines in patients with active UC were significantly higher than those in patients with remittent UC and healthy control subjects (IL-17: 0.0727±0.0037 vs 0.0354±0.0243 vs 0.0330±0.0045; IL-23: 0.1407±0.0068 vs 0.0865±0.0051 vs 0.0442±0.0137; IL-22: 0.0522±0.0045 vs 0.0259±0.0063 vs 0.0115±0.0061; IL-11: 0.0479±0.0022 vs 0.0365±0.0024 vs 0.0232±0.0009, P<0.05).The expression levels of IL-17, IL-23, and IL-22 increased significantly with the increase of the disease activity (IL-17: 0.0545±0.0072 vs 0.0786± 0.0051 vs 0.0847±0.0197; IL-23: 0.1112±0.0046 vs 0.1480±0.0089 vs 0.1644±0.0190; IL-22: 0.0307±0.0063 vs 0.0548±0.0071 vs 0.0719±0.0056, P<0.05). In patients with active UC, the expression levels of the 4 cytokines in the intestinal mucosa were positively correlated with the endoscopic activity grade (P<0.05), and IL-17 and IL-22 expression levels were also positively correlated with the histological grade (P<0.05). All the 4 cytokines were positively intercorrelated. The patients with low IL-17 expression (25.00% ) showed a significantly lower rate of poor mucosal healing than those with high IL-17 expressions (25% vs 67%, P<0.05). Conclusion The cytokines IL-17, IL-23, IL-22, and IL-11 all participate in the pathogenesis of UC and may serve as indicators for evaluating the inflammatory activity. The expression level of IL-17 can be a valuable indicator for predicting mucosal healing in UC patients after a short-term treatment.
Hits
Hits
Downloads
Comment