Incidence of acute Deep Vein Thrombosis in pediatric and adolescent orthopedic trauma hospitalized patients and effect of rivaroxaban treatment.

OBJECTIVE: Deep vein thrombosis (DVT) provoked by orthopedic trauma is increasing in pediatric hospitalized patients. The purpose of our study is to identify the prevalence of acute DVT in pediatric and adolescent orthopedic trauma hospitalized patients and focus on evaluating the anticoagulation strategies and the clinical outcomes after a confirmed acute DVT. METHODS: Patients (age ≤18 years) with a confirmed acute DVT admitted for orthopedic trauma between September 2017 and December 2023 were included. Patients were classified into the non-anticoagulation (NA), the in-hospital anticoagulation (IHA), and the in-and-out-of-hospital anticoagulation (IOHA) groups based on their anticoagulation regimen. Efficacy outcomes were the venous thromboembolism (VTE) recurrence within 3 months and change in thrombus burden by repeat imaging at 2 weeks after discharge compared with baseline. Safety outcomes were major bleeding (MB) and clinically relevant non-major bleeding (CRNMB) within 3 months. RESULTS: Of the 11,206 pediatric and adolescent orthopedic trauma inpatients, 94(median age,16 [15, 18] years) were diagnosed with acute DVT, with an incidence of 0.84 %, of which 8(8.5 %) received NA, 41(43.6 %) received IHA, and 45(47.9 %) received IOHA. After the diagnosis of DVT, of patients who received anticoagulation, 97.9 % were treated with rivaroxaban as an oral anticoagulant, and 71.7 % received an LMWH course of ≥5 days before starting rivaroxaban therapy. With a median anticoagulation course of 22(8, 37.3) days, the duration in the IOHA was significantly longer than the IHA (37 days vs. 8 days, p = 0.000). No patients experienced recurrent VTE and MB at 3 months, and 1 received IOHA had a CRNMB event (0 % vs. 0 % vs. 2.2 %, p = 1.000). Thrombus resolution was significantly higher in patients who received anticoagulation therapy (IOHA 91.1 % vs. IHA 80.5 % vs. NA 37.5 %, P = 0.002), and thrombus-no relevant change was significantly lower in patients who received the IOHA strategy compared with the other groups (4.4 % vs. 19.5 % vs. 62.5 %, P = 0.000). CONCLUSIONS: A rivaroxaban-predominant IOHA strategy significantly reduced the thrombotic burden without increasing the risk of bleeding for the treatment of DVT in adolescents with orthopedic trauma. Duration of anticoagulation therapy <6 weeks appears appropriate for adolescent orthopedic trauma-related DVT.

[Effect of different degrees of primary varus knee on short-term effectiveness of anterior cruciate ligament reconstruction].

Objective: To investigate whether different degrees of primary varus knee affect joint function and stability in patients undergoing anterior cruciate ligament (ACL) reconstruction. Methods: A clinical data of 160 patients with primary varus knee, who were admitted between January 2020 and December 2021 and met the selection criteria, was retrospectively analyzed. All patients underwent primary ACL reconstruction using autologous single-bundle hamstring tendon. Patients were divided into three groups based on the hip-knee-ankle angle (HKA): group A (64 patients with HKA 0°-3°), group B (55 patients with HKA 3°-6°), and group C (41 patients with HKA 6°-9°). Except for the significant difference in HKA among the three groups ( P<0.05), baseline data such as age, gender, affected side, body mass index, interval between injury and operation, Kellgren-Lawrence grading, posterior tibial slope, proportion of combined meniscal injuries, Tegner score, Lysholm score, and International Knee Documentation Committee (IKDC) objective score, anterior drawer test, Lachman test, pivot shift test, and the results of KT1000 (side-to-side difference, SSD) showed no significant difference ( P>0.05). At last follow-up, joint stability was assessed through the anterior drawer test, Lachman test, pivot shift test, and SSD; joint function was evaluated using the Tegner score, Lysholm score, and IKDC objective score. Results: All incisions in the three groups healed by first intention after operation. All patients were followed up 24-31 months, with an average of 26 months; there was no significant difference in the follow-up time among the three groups ( Z=0.675, P=0.714). At last follow-up, the knee stability and functional assessment indicators in each group significantly improved when compared to preoperative ones ( P<0.05); there was no significant difference among the three groups ( P>0.05) in terms of the anterior drawer test, Lachman test, pivot shift test, IKDC objective scores, and the changes of the Lysholm scores and Tegner scores. The Kellgren-Lawrence grading and HKA at last follow-up were consistent with preoperative results in the three groups. Conclusion: Varying degrees of primary varus knee do not affect early knee joint stability and functional recovery after ACL reconstruction, and there is no significant difference in effectiveness between different degrees of varus knee.

It is time to move forward: a bibliometric analysis of top 50 cited articles in elbow arthroscopy.

OBJECTIVES: To analyze the bibliometric characteristics of the top 50 cited articles in elbow arthroscopy. METHODS: The Web of Science Core Collection was employed to systematically retrieve publications related to elbow arthroscopy. Subsequently, the top 50 cited articles meeting the predefined inclusion criteria were meticulously documented and subjected to comprehensive bibliometric analysis. RESULTS: The top 50 cited articles spanned the years 1999-2017, with the 2010s emerging as the most prolific decade. Citations per article varied from 24 to 211, and citation density ranged from 1.61 to 9.17. The United States dominated in article production and citations. Predominantly, the articles took the form of case series and expert opinions, with a notable absence of level I or II evidence. The keywords with the highest frequencies were "arthrofibrosis," "complications," and "release." These keywords formed five main clusters: stiff elbow, osteoarthritis, osteochondritis dissecans, and lateral epicondylitis. CONCLUSIONS: The majority of the top 50 cited articles in elbow arthroscopy comprised case series exhibiting Level IV or V evidence. Despite a dynamic development post-2010, elbow arthroscopy articles showed lower mean citations and citation density compared to other joints, potentially influenced by concerns about complications. However, with the increasing prevalence of elbow arthroscopy procedures, it is anticipated that higher-level articles, particularly those focusing on complications and exploring additional indications, will supersede some of the articles included in this analysis. LEVEL OF EVIDENCE: IV.

Topical Use of Low-dose Tranexamic Acid Has no Effect on Drainage Volume after Medial Open Wedge High Tibial Osteotomy: A Case Control Study.

OBJECTIVE: Many studies reported that tranexamic acid (TXA) was effective in reducing surgical blood loss in the perioperative period of medial open wedge high tibial osteotomy (MOWHTO). However, few studies focused on the simple topical use of TXA in MOWHTO, and the modality and dosage of topical use of TXA varied. The purpose of this study was to observe the effect of topical use of low-dose TXA on drainage volume after MOWHTO, and to analyze the related influencing factors. METHODS: Data of patients who underwent MOWHTO combined with arthroscopic knee surgery in our department from January 2019 to September 2021 were retrospectively analyzed. A total of 105 patients (38 males and 67 females, aged 57.7 ± 7.5 years) were included in this study who received topical TXA or no TXA. The patients were divided into three groups: control group (39 cases), 0.5 g TXA group (40 cases), 1 g TXA group (26 cases). Postoperative drainage volume, wound healing, incidence of hematoma and deep venous thrombosis (DVT) were observed and analyzed in the three groups. The effects of gender, hypertension and diabetes on postoperative drainage volume were analyzed using a t-test. The correlation between age, body mass index (BMI), osteotomy gap and postoperative drainage volume were analyzed using the Pearson correlation coefficient. RESULTS: The average postoperative drainage volume of the control group was 259.54 ± 226.33 mL, that of the 0.5 g TXA group was 277.18 ± 177.68 mL, and that of the 1 g TXA group was 229.15 ± 219.93 mL. There was no statistically significant difference in postoperative drainage volume among the three groups (F = 0.423, p = 0.656). There was no local hematoma and wound infection in the three groups. The wound fat liquefaction was found in one patient of the control group. The incidence of DVT was 38.9% (7/18) and 57.1% (8/14) in the control group and 0.5 TXA group, respectively. There was no significant difference in the incidence of DVT between the above two groups (p = 0.476). The average postoperative drainage volume of male patients in the three groups was higher than that of female patients, and the differences were statistically significant (p < 0.05). There was no correlation between age, BMI, osteotomy gap and postoperative drainage volume in the three groups (p > 0.05). CONCLUSION: Topical use of low-dose TXA has no significant effect on drainage volume after MOWHTO. The drainage volume after MOWHTO in male patients was more than that in female patients. Topical administration of low-dose TXA does not increase postoperative complications, such as DVT and hematoma.

[Research progress on pathological mechanism and clinical correlation between medial meniscus posterior root tear and tibial rotation].

Objective: To summarize the current research progress on the concept, clinical presentation, diagnosis, biomechanical changes, and pathological mechanisms of the medial meniscus posterior root tear (MMPRT), and its clinical correlations with tibial rotation. Methods: The research literature on MMPRT and its relationship with tibial rotation at home and abroad in recent years was extensively consulted and summarized. Results: MMPRT is a specific and common type of medial meniscus injury of the knee joint. The occurrence of posterior medial pumping pain events following low-energy trauma in patients provides important clues for the diagnosis of this injury, with MRI being the preferred imaging modality. The biomechanical effects generated by MMPRT are similar to those caused by total removal of the medial meniscus. And this injury is usually associated with tibial rotation. MMPRT induces pathological external rotation of the tibia, which can be restored by timely medial meniscus posterior root repair. Furthermore, changes in tibial rotation are related to the healing status after medial meniscus posterior root repair. Conclusion: MMPRT is closely related to tibial rotation. Understanding the biomechanics, pathological mechanisms, and clinical correlations between the two is of great significance for improving the diagnosis and treatment strategies.

[Study on clinical characteristics and surgical methods of bucket-handle meniscal tears].

Objective: To summarize the clinical features, surgical methods, and prognosis of bucket-handle meniscal tears (BHMTs), and provide guidance for clinical treatment. Methods: The clinical data of 91 BHMTs patients (91 knees), who met the selection criteria and were admitted between January 2015 and January 2021, was retrospectively analyzed. There were 68 males and 23 females. Age ranged from 16 to 58 years with an average of 34.4 years. The injury was caused by sports in 68 cases, traffic accident in 15 cases, and falls or sprains in 8 cases. There were 49 cases of left knee injury and 42 cases of right knee injury. The time from the onset of symptoms to the admission ranged from 1 day to 13 months (median, 18 days), including >1 month in 35 cases and ≤1 month in 56 cases. Medial BHMTs occurred in 52 cases and lateral BHMTs in 39 cases. There were 36 cases with ACL rupture and 12 cases with discoid meniscus. The knee extension was limited more than 10° in 55 cases. According to the condition of meniscus injury, the meniscus suture with Inside-out combined with All-inside techniques (54 cases) or meniscoplasty (37 cases) under arthroscopy were selected. ACL reconstruction was performed in all patients with ACL rupture with autogenous hamstring tendon. Postoperative complications were observed. International Knee Documentation Committee (IKDC) score, Lysholm score, and Tegner score were used to evaluate knee function, and clinical failure was recorded. Results: Two patients developed intermuscular venous thrombosis, which improved after oral anticoagulant therapy. No vascular injury, postoperative infection, joint stiffness, or other complications occurred in all patients. All patients were followed up 24-95 months, with a median of 64 months. A total of 12 cases (13.19%) failed the operation and were re-operated or given oral anti-inflammatory analgesics and rehabilitation therapy. At last follow-up, IKDC score and Lysholm score of 91 patients significantly increased when compared with those before operation ( P<0.05), while Tegner score significantly decreased ( P<0.05). The above indexes of patients treated with meniscus suture and meniscoplasty were also significantly different from those before operation ( P<0.05). Conclusion: BHMTs occurs mostly in young men and is one of the important reasons for the limitation of knee extension after trauma. Arthroscopic meniscus suture and meniscoplasty can obtain good effectiveness according to individual conditions of patients. But the latter can better preserve the shape and function of meniscus, and theoretically can obtain better long-term outcomes, which needs to be confirmed by further research with larger sample size.

Enhancing Offensive Language Detection with Data Augmentation and Knowledge Distillation.

Offensive language detection has received important attention and plays a crucial role in promoting healthy communication on social platforms, as well as promoting the safe deployment of large language models. Training data is the basis for developing detectors; however, the available offense-related dataset in Chinese is severely limited in terms of data scale and coverage when compared to English resources. This significantly affects the accuracy of Chinese offensive language detectors in practical applications, especially when dealing with hard cases or out-of-domain samples. To alleviate the limitations posed by available datasets, we introduce AugCOLD (Augmented Chinese Offensive Language Dataset), a large-scale unsupervised dataset containing 1 million samples gathered by data crawling and model generation. Furthermore, we employ a multiteacher distillation framework to enhance detection performance with unsupervised data. That is, we build multiple teachers with publicly accessible datasets and use them to assign soft labels to AugCOLD. The soft labels serve as a bridge for knowledge to be distilled from both AugCOLD and multiteacher to the student network, i.e., the final offensive detector. We conduct experiments on multiple public test sets and our well-designed hard tests, demonstrating that our proposal can effectively improve the generalization and robustness of the offensive language detector.

A Fuzzy Clustering Validity Index Induced by Triple Center Relation.

The existing clustering validity indexes (CVIs) show some difficulties to produce the correct cluster number when some cluster centers are close to each other, and the separation processing mechanism appears simple. The results are imperfect in case of noisy data sets. For this reason, in this study, we come up with a novel CVI for fuzzy clustering, referred to as the triple center relation (TCR) index. The originality of this index is twofold. On the one hand, a new fuzzy cardinality is built on the strength of the maximum membership degree, and a novel compactness formula is constructed by combining it with the within-class weighted squared error sum. On the other hand, starting from the minimum distance between different cluster centers, the mean distance as well as the sample variance of cluster centers in the statistical sense are further integrated. These three factors are combined by means of product to form a triple characterization of the relationship between cluster centers, and hence a 3-D expression pattern of separability is formed. Subsequently, the TCR index is put forward by combining the compactness formula with the separability expression pattern. By virtue of the degenerate structure of hard clustering, we show an important property of the TCR index. Finally, based on the fuzzy C -means (FCMs) clustering algorithm, experimental studies were conducted on 36 data sets (incorporating artificial and UCI data sets, images, the Olivetti face database). For comparative purposes, 10 CVIs were also considered. It has been found that the proposed TCR index performs best in finding the correct cluster number, and has excellent stability.

Arthroscopy combined with high tibial osteotomy promotes cartilage regeneration in osteoarthritis.

BACKGROUND: To investigate the effect of arthroscopy combined with high tibial osteotomy (HTO) on cartilage regeneration in patients with knee osteoarthritis. METHODS: A retrospective analysis of 50 patients with varus and medial compartment osteoarthritis of the knee treated by arthroscopy combined with HTO. One year after the operation, a second-look arthroscopy was performed to observe the cartilage regeneration. The regeneration of cartilage was evaluated by different pathological staining of some of the new cartilage. Finally, part of the new cartilages (n = 6) were taken for quantitative real-time PCR and western blotting experiments to display the mechanism of cartilage regeneration. RESULTS: One year after arthroscopy combined with HTO, the results of arthroscopy revealed the formation of new tissue in the defect area of the medial compartment's cartilage in the knee joint. In addition, different pathological staining results indicated that the new tissue was cartilage-like tissue. Furthermore, HTO potently up-regulated the expression of p-ERK1/2 at the protein level in knee osteoarthritis patients compared with control group. However, there was no significant difference in the relative expression of collagen II at mRNA and protein level between control group and knee osteoarthritis patients. CONCLUSION: Arthroscopy combined with HTO can promote cartilage regeneration in patients with knee osteoarthritis.

[Management status of anterior cruciate ligament injury in children and adolescents].

Objective: To summarize the current management of anterior cruciate ligament (ACL) injury in children and adolescents, in order to provide reference for the management of ACL injury in children and adolescents. Methods: The relevant literature at home and abroad in recent years was extensively accessed to summarize the management status of ACL injury in children and adolescent. Results: The number of ACL injury in children and adolescents is increasing every year. The diagnosis of ACL mainly depends on symptoms and signs. Rehabilitation, physeal-sparing techniques, partial transphyseal techniques, all-epiphyseal techniques, and transphyseal techniques are used to treat ACL injury in children and adolescents. Conclusion: Dynamic monitoring of knee joint in children and adolescents should be strengthened. The best treatment for ACL injury in children and adolescents is selected according to the patients' actual age, bone age, Tanner stage, and physiological conditions such as menstruation, body growth speed, and other characteristics.

[Experience in diagnosis and treatment of KD- â ¢M dislocation of knee joint].

OBJECTIVE: To explore the effectiveness of one-stage posterior medial corner (PMC) repair or reconstruction combined with anterior cruciate ligament (ACL) and posterior cruciate ligament (PCL) reconstruction in treating KD-ⅢM dislocation. METHODS: The clinical data of 15 patients with knee KD-ⅢM dislocation who met the selection criteria between January 2016 and July 2019 were retrospectively analyzed. There were 9 males and 6 females, aged 22-61 years (mean, 40.3 years). Injuries were caused by violence of flexion, valgus, and external rotation, including 10 cases of traffic accident injuries, 3 cases of crush injuries, 1 case of winch injury, and 1 case of explosion injury. The time from injury to operation ranged from 3 days to 6 months, with an average of 18.5 days. PMC repair combined with PCL+ACL reconstruction was performed in 10 cases in acute stage (within 3 weeks after injury), including 3 cases of irreducible dislocation. PMC+PCL+ACL reconstruction was performed in 5 cases with chronic dislocation. Before operation and at last follow-up, the knee joint function was evaluated by Lysholm score and International Knee Documentation Committee (IKDC) 2000 score. KT-3000 was used to evaluate the forward stability of the knee (calculated the difference of tibial anterior displacement of both knees), the X-ray films of the stress position of the knee joint was used to evaluate the valgus of the knee (calculated the difference of medial joint space width of both knees) and the backward stability (calculated the difference of tibial posterior displacement of both knees), and the internal and external rotation stability was evaluated by knee flexion 30° tibial external rotation and knee flexion 90° tibial internal rotation tests (calculated the difference of tibial internal rotation and the difference of tibial external rotation of both knees). RESULTS: The operation time was 120-240 minutes, with an average of 186.5 minutes. Patients were followed up 24-48 months, with an average of 27.4 months. There was no complication such as infection, deep vein thrombosis, vascular injury, or heterotopic ossification. At last follow-up, the Lysholm score, IKDC2000 score, the difference of tibial anterior displacement of both knees, the difference of medial joint space width of both knees, the difference of tibial posterior displacement of both knees, the difference of tibial internal rotation and the difference of tibial external rotation of both knees significantly improved when compared with preoperative ones ( P<0.05). According to the IKDC2000 valgus stability grading standard, there were 3 cases of grade C and 12 cases of grade D before operation, and 10 cases of grade A and 5 cases of grade B at last follow-up, which was significantly improved when compared with that before operation ( Z=-4.930, P=0.000). At last follow-up, the pivot shift tests of 15 patients were negative. The anterior and posterior drawer tests of 10 patients were negative, 5 patients had mild instability, both the anterior and posterior drawer tests were positive. CONCLUSION: KD-ⅢM dislocation of the knee joint can lead to the posterior medial and anterior instability. Acute dislocation combined with "dimple sign" requires surgical reduction as soon as possible to repair PMC and reconstruct PCL and ACL. In chronic patients, PMC is difficult to repair, it is recommended to reconstruct PMC, PCL, and ACL at one stage to improve knee joint stability. The early and middle effectiveness are satisfactory.

Hierarchical Network with Label Embedding for Contextual Emotion Recognition.

Emotion recognition has been used widely in various applications such as mental health monitoring and emotional management. Usually, emotion recognition is regarded as a text classification task. Emotion recognition is a more complex problem, and the relations of emotions expressed in a text are nonnegligible. In this paper, a hierarchical model with label embedding is proposed for contextual emotion recognition. Especially, a hierarchical model is utilized to learn the emotional representation of a given sentence based on its contextual information. To give emotion correlation-based recognition, a label embedding matrix is trained by joint learning, which contributes to the final prediction. Comparison experiments are conducted on Chinese emotional corpus RenCECps, and the experimental results indicate that our approach has a satisfying performance in textual emotion recognition task.

CERG: Chinese Emotional Response Generator with Retrieval Method.

The dialogue system has always been one of the important topics in the domain of artificial intelligence. So far, most of the mature dialogue systems are task-oriented based, while non-task-oriented dialogue systems still have a lot of room for improvement. We propose a data-driven non-task-oriented dialogue generator "CERG" based on neural networks. This model has the emotion recognition capability and can generate corresponding responses. The data set we adopt comes from the NTCIR-14 STC-3 CECG subtask, which contains more than 1.7 million Chinese Weibo post-response pairs and 6 emotion categories. We try to concatenate the post and the response with the emotion, then mask the response part of the input text character by character to emulate the encoder-decoder framework. We use the improved transformer blocks as the core to build the model and add regularization methods to alleviate the problems of overcorrection and exposure bias. We introduce the retrieval method to the inference process to improve the semantic relevance of generated responses. The results of the manual evaluation show that our proposed model can make different responses to different emotions to improve the human-computer interaction experience. This model can be applied to lots of domains, such as automatic reply robots of social application.

A Robust Parameter-free Thresholding Method for Image Segmentation.

In this work we presented a new parameter-free thresholding method for image segmentation. In separating an image into two classes, the method employs an objective function that not only maximizes the between-class variance but also the distance between the mean of each class and the global mean of the image. The design of the objective function aims to circumvent the challenge that many existing techniques encounter when the underlying two classes have very different sizes or variances. Advantages of the new method are two-fold. First, it is parameter-free, meaning that it can generate consistent results. Second, the new method has a simple form that makes it easy to adapt to different applications. We tested and compared the new method with the standard Otsu method, the maximum entropy method, and the 2D Otsu method on simulated and real biomedical and photographic images and found the new method can achieve a more accurate and robust performance.

Reinforcement Emotion-Cognition System: A Teaching Words Task.

The goal of this paper is to suggest a system for intelligent learning environments with robots modeling of emotion regulation and cognition based on quantitative motivation. A detailed interactive situation for teaching words is proposed. In this study, we introduce one bottom-up collaboration method for emotion-cognition interplay and behaviour decision-making. Integration with gross emotion regulation theory lets the proposed system adapt to natural interactions between students and the robot in emotional interaction. Four key ideas are advocated, and they jointly set up a reinforcement emotion-cognition system (RECS). First, the quantitative motivation is grounded on external interactive sensory detection, which is affected by memory and preference. Second, the emotion generation triggered by an initial motivation such as external stimulus is also influenced by the state in the previous time. Third, the competitive and cooperative relationship between emotion and motivation intervenes to make the decision of emotional expression and teaching actions. Finally, cognitive reappraisal, the emotion regulation strategy, is introduced for the establishment of emotion transition combined with personalized cognition. We display that this RECS increases the robot emotional interactive performance and makes corresponding teaching decision through behavioural and statistical analysis.

Emotion classification using a CNN_LSTM-based model for smooth emotional synchronization of the humanoid robot REN-XIN.

In this paper, we propose an Emotional Trigger System to impart an automatic emotion expression ability within the humanoid robot REN-XIN, in which the Emotional Trigger is an emotion classification model trained from our proposed Word Mover's Distance(WMD) based algorithm. Due to the long time delay of the WMD-based Emotional Trigger System, we propose an enhanced Emotional Trigger System to enable a smooth interaction with the robot in which the Emotional Trigger is replaced by a conventional convolution neural network and a long short term memory network (CNN_LSTM)-based deep neural network. In our experiments, the CNN_LSTM based model only need 10 milliseconds or less to finish the classification without a decrease in accuracy, while the WMD-based model needed approximately 6-8 seconds to give a result. In this paper, the experiments are conducted based on the same sub-data sets of the Chinese emotional corpus(Ren_CECps) used in former WMD experiments: one comprises 50% data for training and 50% for testing(1v1 experiment), and the other comprises 80% data for training and 20% for testing(4v1 experiment). The experiments are conducted using WMD, CNN_LSTM, CNN and LSTM. The results show that CNN_LSTM obtains the best F1 score (0.35) in the 1v1 experiment and almost the same accuracy of F1 scores (0.366 vs 0.367) achieved by WMD in the 4v1 experiment. Finally, we present demonstration videos with the same scenario to show the performance of robot control driven by CNN_LSTM-based Emotional Trigger System and WMD-based Emotional Trigger System. To improve the comparison, total manual-control performance is also recorded.

Emotion computing using Word Mover's Distance features based on Ren_CECps.

In this paper, we propose an emotion separated method(SeTF·IDF) to assign the emotion labels of sentences with different values, which has a better visual effect compared with the values represented by TF·IDF in the visualization of a multi-label Chinese emotional corpus Ren_CECps. Inspired by the enormous improvement of the visualization map propelled by the changed distances among the sentences, we being the first group utilizes the Word Mover's Distance(WMD) algorithm as a way of feature representation in Chinese text emotion classification. Our experiments show that both in 80% for training, 20% for testing and 50% for training, 50% for testing experiments of Ren_CECps, WMD features get the best f1 scores and have a greater increase compared with the same dimension feature vectors obtained by dimension reduction TF·IDF method. Compared experiments in English corpus also show the efficiency of WMD features in the cross-language field.