DEFINE: friendship detection based on node enhancement
- Pan, Hanxiao, Guo, Teng, Bedru, Hayat, Qing, Qing, Zhang, Dongyu, Xia, Feng
- Authors: Pan, Hanxiao , Guo, Teng , Bedru, Hayat , Qing, Qing , Zhang, Dongyu , Xia, Feng
- Date: 2020
- Type: Text , Conference paper
- Relation: 31st Australasian Database Conference, ADC 2019 Vol. 12008 LNCS, p. 81-92
- Full Text:
- Reviewed:
- Description: Network representation learning (NRL) is a matter of importance to a variety of tasks such as link prediction. Learning low-dimensional vector representations for node enhancement based on nodes attributes and network structures can improve link prediction performance. Node attributes are important factors in forming networks, like psychological factors and appearance features affecting friendship networks. However, little to no work has detected friendship using the NRL technique, which combines students’ psychological features and perceived traits based on facial appearance. In this paper, we propose a framework named DEFINE (No enhancement based r e dship D tection) to detect students’ friend relationships, which combines with students’ psychological factors and facial perception information. To detect friend relationships accurately, DEFINE uses the NRL technique, which considers network structure and the additional attributes information for nodes. DEFINE transforms them into low-dimensional vector spaces while preserving the inherent properties of the friendship network. Experimental results on real-world friendship network datasets illustrate that DEFINE outperforms other state-of-art methods. © 2020, Springer Nature Switzerland AG.
- Description: E1
- Authors: Pan, Hanxiao , Guo, Teng , Bedru, Hayat , Qing, Qing , Zhang, Dongyu , Xia, Feng
- Date: 2020
- Type: Text , Conference paper
- Relation: 31st Australasian Database Conference, ADC 2019 Vol. 12008 LNCS, p. 81-92
- Full Text:
- Reviewed:
- Description: Network representation learning (NRL) is a matter of importance to a variety of tasks such as link prediction. Learning low-dimensional vector representations for node enhancement based on nodes attributes and network structures can improve link prediction performance. Node attributes are important factors in forming networks, like psychological factors and appearance features affecting friendship networks. However, little to no work has detected friendship using the NRL technique, which combines students’ psychological features and perceived traits based on facial appearance. In this paper, we propose a framework named DEFINE (No enhancement based r e dship D tection) to detect students’ friend relationships, which combines with students’ psychological factors and facial perception information. To detect friend relationships accurately, DEFINE uses the NRL technique, which considers network structure and the additional attributes information for nodes. DEFINE transforms them into low-dimensional vector spaces while preserving the inherent properties of the friendship network. Experimental results on real-world friendship network datasets illustrate that DEFINE outperforms other state-of-art methods. © 2020, Springer Nature Switzerland AG.
- Description: E1
Graduate employment prediction with bias
- Guo, Teng, Xia, Feng, Zhen, Shihao, Bai, Xiaomei, Zhang, Dongyu
- Authors: Guo, Teng , Xia, Feng , Zhen, Shihao , Bai, Xiaomei , Zhang, Dongyu
- Date: 2020
- Type: Text , Conference paper
- Relation: AAAI 2020 - 34th AAAI Conference on Artificial Intelligence p. 670-677
- Full Text:
- Reviewed:
- Description: The failure of landing a job for college students could cause serious social consequences such as drunkenness and suicide. In addition to academic performance, unconscious biases can become one key obstacle for hunting jobs for graduating students. Thus, it is necessary to understand these unconscious biases so that we can help these students at an early stage with more personalized intervention. In this paper, we develop a framework, i.e., MAYA (Multi-mAjor emploYment stAtus) to predict students’ employment status while considering biases. The framework consists of four major components. Firstly, we solve the heterogeneity of student courses by embedding academic performance into a unified space. Then, we apply a generative adversarial network (GAN) to overcome the class imbalance problem. Thirdly, we adopt Long Short-Term Memory (LSTM) with a novel dropout mechanism to comprehensively capture sequential information among semesters. Finally, we design a bias-based regularization to capture the job market biases. We conduct extensive experiments on a large-scale educational dataset and the results demonstrate the effectiveness of our prediction framework. Copyright © 2020, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Feng Xia” is provided in this record**
- Authors: Guo, Teng , Xia, Feng , Zhen, Shihao , Bai, Xiaomei , Zhang, Dongyu
- Date: 2020
- Type: Text , Conference paper
- Relation: AAAI 2020 - 34th AAAI Conference on Artificial Intelligence p. 670-677
- Full Text:
- Reviewed:
- Description: The failure of landing a job for college students could cause serious social consequences such as drunkenness and suicide. In addition to academic performance, unconscious biases can become one key obstacle for hunting jobs for graduating students. Thus, it is necessary to understand these unconscious biases so that we can help these students at an early stage with more personalized intervention. In this paper, we develop a framework, i.e., MAYA (Multi-mAjor emploYment stAtus) to predict students’ employment status while considering biases. The framework consists of four major components. Firstly, we solve the heterogeneity of student courses by embedding academic performance into a unified space. Then, we apply a generative adversarial network (GAN) to overcome the class imbalance problem. Thirdly, we adopt Long Short-Term Memory (LSTM) with a novel dropout mechanism to comprehensively capture sequential information among semesters. Finally, we design a bias-based regularization to capture the job market biases. We conduct extensive experiments on a large-scale educational dataset and the results demonstrate the effectiveness of our prediction framework. Copyright © 2020, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Feng Xia” is provided in this record**
ANSWER : generating information dissemination network on campus
- Qing, Qing, Guo, Teng, Zhang, Dongyu, Xia, Feng
- Authors: Qing, Qing , Guo, Teng , Zhang, Dongyu , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 32nd Australasian Database Conference, ADC 2021 Vol. 12610 LNCS, p. 74-86
- Full Text:
- Reviewed:
- Description: Information dissemination matters, both on an individual and group level. For college students who are physically and mentally immature, they are more sensitive and susceptible to unnormal information like rumors. However, current researches focus on large-scale online message sharing networks like Facebook and Twitter, rather than profile the information dissemination on campus, which fail to provide any references for daily campus management. Against this background, we propose a framework to generate the information dissemination network on campus, named ANSWER (cAmpus iNformation diSsemination netWork gEneRation), based on multimodal data including behavior data, appearance data, and psychological data. The construction of the ANSWER is listed as four steps. First, we use a convolutional autoencoder to extract the students’ facial features. Second, we process the behavior data to construct a friendship network. Third, heterogeneous information is embedded in the low-dimensional vector space by using network representation learning to obtain embedding vectors. Fourth, we use the deep learning model to predict. The experiment results show that ANSWER outperforms other methods in multiple feature fusion and prediction of information dissemination relationship performance. © 2021, Springer Nature Switzerland AG.
- Authors: Qing, Qing , Guo, Teng , Zhang, Dongyu , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 32nd Australasian Database Conference, ADC 2021 Vol. 12610 LNCS, p. 74-86
- Full Text:
- Reviewed:
- Description: Information dissemination matters, both on an individual and group level. For college students who are physically and mentally immature, they are more sensitive and susceptible to unnormal information like rumors. However, current researches focus on large-scale online message sharing networks like Facebook and Twitter, rather than profile the information dissemination on campus, which fail to provide any references for daily campus management. Against this background, we propose a framework to generate the information dissemination network on campus, named ANSWER (cAmpus iNformation diSsemination netWork gEneRation), based on multimodal data including behavior data, appearance data, and psychological data. The construction of the ANSWER is listed as four steps. First, we use a convolutional autoencoder to extract the students’ facial features. Second, we process the behavior data to construct a friendship network. Third, heterogeneous information is embedded in the low-dimensional vector space by using network representation learning to obtain embedding vectors. Fourth, we use the deep learning model to predict. The experiment results show that ANSWER outperforms other methods in multiple feature fusion and prediction of information dissemination relationship performance. © 2021, Springer Nature Switzerland AG.
Web of students : class-level friendship network discovery from educational big data
- Guo, Teng, Tang, Tang, Zhang, Dongyu, Li, Jianxin, Xia, Feng
- Authors: Guo, Teng , Tang, Tang , Zhang, Dongyu , Li, Jianxin , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 22nd International Conference on Web Information Systems Engineering, WISE 2021 p. 497-511
- Full Text: false
- Reviewed:
- Description: Classmate friendships are a major aspect of university social experience. Taking classes together is one of the main ways for students to build friendships. Consequently, class-level friendship networks have attracted tremendous attention from researchers. They are also very useful in student support and early intervention. However, these networks are normally invisible for educators. Discovering such an important web of students effectively is a pressing problem. Against this background, we propose a data-driven framework called CANDY which automatically discovers the class-level friendship networks based on educational big data. We first represent features through representation learning methods. Secondly, the data is augmented with the randomly shuffling method. Thirdly, a conditional generative adversarial network model is used to mine the class-level friendship networks. A deep adversarial optimization strategy is proposed here for problems caused by network sparsity. To evaluate the performance of the proposed approach, we build a real-world dataset that contains rich student information. Extensive experiments have been conducted and the results demonstrate the effectiveness of our framework. © 2021, Springer Nature Switzerland AG.
Network embedding : taxonomies, frameworks and applications
- Hou, Mingliang, Ren, Jing, Zhang, Da, Kong, Xiangjie, Zhang, Dongyu, Xia, Feng
- Authors: Hou, Mingliang , Ren, Jing , Zhang, Da , Kong, Xiangjie , Zhang, Dongyu , Xia, Feng
- Date: 2020
- Type: Text , Journal article , Review
- Relation: Computer Science Review Vol. 38, no. (2020), p.
- Full Text:
- Reviewed:
- Description: Networks are a general language for describing complex systems of interacting entities. In the real world, a network always contains massive nodes, edges and additional complex information which leads to high complexity in computing and analyzing tasks. Network embedding aims at transforming one network into a low dimensional vector space which benefits the downstream network analysis tasks. In this survey, we provide a systematic overview of network embedding techniques in addressing challenges appearing in networks. We first introduce concepts and challenges in network embedding. Afterwards, we categorize network embedding methods using three categories, including static homogeneous network embedding methods, static heterogeneous network embedding methods and dynamic network embedding methods. Next, we summarize the datasets and evaluation tasks commonly used in network embedding. Finally, we discuss several future directions in this field. © 2020 Elsevier Inc.
- Authors: Hou, Mingliang , Ren, Jing , Zhang, Da , Kong, Xiangjie , Zhang, Dongyu , Xia, Feng
- Date: 2020
- Type: Text , Journal article , Review
- Relation: Computer Science Review Vol. 38, no. (2020), p.
- Full Text:
- Reviewed:
- Description: Networks are a general language for describing complex systems of interacting entities. In the real world, a network always contains massive nodes, edges and additional complex information which leads to high complexity in computing and analyzing tasks. Network embedding aims at transforming one network into a low dimensional vector space which benefits the downstream network analysis tasks. In this survey, we provide a systematic overview of network embedding techniques in addressing challenges appearing in networks. We first introduce concepts and challenges in network embedding. Afterwards, we categorize network embedding methods using three categories, including static homogeneous network embedding methods, static heterogeneous network embedding methods and dynamic network embedding methods. Next, we summarize the datasets and evaluation tasks commonly used in network embedding. Finally, we discuss several future directions in this field. © 2020 Elsevier Inc.
Metaphor research in the 21st century : a bibliographic analysis
- Zhang, Dongyu, Zhang, Minghao, Peng, Ciyuan, Jung, Jason, Xia, Feng
- Authors: Zhang, Dongyu , Zhang, Minghao , Peng, Ciyuan , Jung, Jason , Xia, Feng
- Date: 2020
- Type: Text , Journal article
- Relation: Computer Science and Information Systems Vol. 18, no. 1 (2020), p. 303-322
- Full Text:
- Reviewed:
- Description: Metaphor is widely used in human communication. The cohort of scholars studying metaphor in various fields is continuously growing, but very few work has been done in bibliographical analysis of metaphor research. This paper examines the advancements in metaphor research from 2000 to 2017. Using data retrieved from Microsoft Academic Graph and Web of Science, this paper makes a macro analysis of metaphor research, and expounds the underlying patterns of its development. Taking into consideration sub-fields of metaphor research, the internal analysis of metaphor research is carried out from a micro perspective to reveal the evolution of research topics and the inherent relationships among them. This paper provides novel insights into the current state of the art of metaphor research as well as future trends in this field, which may spark new research interests in metaphor from both linguistic and interdisciplinary perspectives. © 2020, ComSIS Consortium. All rights reserved.
- Authors: Zhang, Dongyu , Zhang, Minghao , Peng, Ciyuan , Jung, Jason , Xia, Feng
- Date: 2020
- Type: Text , Journal article
- Relation: Computer Science and Information Systems Vol. 18, no. 1 (2020), p. 303-322
- Full Text:
- Reviewed:
- Description: Metaphor is widely used in human communication. The cohort of scholars studying metaphor in various fields is continuously growing, but very few work has been done in bibliographical analysis of metaphor research. This paper examines the advancements in metaphor research from 2000 to 2017. Using data retrieved from Microsoft Academic Graph and Web of Science, this paper makes a macro analysis of metaphor research, and expounds the underlying patterns of its development. Taking into consideration sub-fields of metaphor research, the internal analysis of metaphor research is carried out from a micro perspective to reveal the evolution of research topics and the inherent relationships among them. This paper provides novel insights into the current state of the art of metaphor research as well as future trends in this field, which may spark new research interests in metaphor from both linguistic and interdisciplinary perspectives. © 2020, ComSIS Consortium. All rights reserved.
Telling the whole story : a manually annotated Chinese dataset for the analysis of humor in jokes
- Zhang, Dongyu, Zhang, Heting, Liu, Xikai, Lin, Hongfei, Xia, Feng
- Authors: Zhang, Dongyu , Zhang, Heting , Liu, Xikai , Lin, Hongfei , Xia, Feng
- Date: 2019
- Type: Text , Conference paper
- Relation: 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, 3 to 7 November 2019, EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference p. 6402-6407
- Full Text:
- Reviewed:
- Description: Humor plays important role in human communication, which makes it important problem for natural language processing. Prior work on the analysis of humor focuses on whether text is humorous or not, or the degree of funniness, but this is insufficient to explain why it is funny. We therefore create a dataset on humor with 9,123 manually annotated jokes in Chinese. We propose a novel annotation scheme to give scenarios of how humor arises in text. Specifically, our annotations of linguistic humor not only contain the degree of funniness, like previous work, but they also contain key words that trigger humor as well as character relationship, scene, and humor categories. We report reasonable agreement between annotators. We also conduct an analysis and exploration of the dataset. To the best of our knowledge, we are the first to approach humor annotation for exploring the underlying mechanism of the use of humor, which may contribute to a significantly deeper analysis of humor. We also contribute with a scarce and valuable dataset, which we will release publicly. © 2019 Association for Computational Linguistics
- Authors: Zhang, Dongyu , Zhang, Heting , Liu, Xikai , Lin, Hongfei , Xia, Feng
- Date: 2019
- Type: Text , Conference paper
- Relation: 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, 3 to 7 November 2019, EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference p. 6402-6407
- Full Text:
- Reviewed:
- Description: Humor plays important role in human communication, which makes it important problem for natural language processing. Prior work on the analysis of humor focuses on whether text is humorous or not, or the degree of funniness, but this is insufficient to explain why it is funny. We therefore create a dataset on humor with 9,123 manually annotated jokes in Chinese. We propose a novel annotation scheme to give scenarios of how humor arises in text. Specifically, our annotations of linguistic humor not only contain the degree of funniness, like previous work, but they also contain key words that trigger humor as well as character relationship, scene, and humor categories. We report reasonable agreement between annotators. We also conduct an analysis and exploration of the dataset. To the best of our knowledge, we are the first to approach humor annotation for exploring the underlying mechanism of the use of humor, which may contribute to a significantly deeper analysis of humor. We also contribute with a scarce and valuable dataset, which we will release publicly. © 2019 Association for Computational Linguistics
Predicting mental health problems with personality, behavior, and social networks
- Zhang, Dongyu, Guo, Teng, Han, Shiyu, Vahabli, Sadaf, Naseriparsa, Mehdi, Xia, Feng
- Authors: Zhang, Dongyu , Guo, Teng , Han, Shiyu , Vahabli, Sadaf , Naseriparsa, Mehdi , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE International Conference on Big Data, Big Data 2021, virtual online, 15-18 December 2021, Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021 p. 4537-4546
- Full Text:
- Reviewed:
- Description: Mental health is an integral part of human health and well-being. Unhealthy mentality leads to serious consequences such as self-mutilation and suicide, especially for college students. While the literature focused on analysing the relationship between mental health and a single factor such as personality or behavior, accurate prediction is yet to be achieved due to the lack of cross-dimensional analysis and multi-dimensional joint prediction. To this end, this work proposes leveraging multiple factors from three crucial dimensions of mental health: behaviors, personality, and social networks. We recruited 490 college students, and collected their behavioral records from smart cards. In addition, we extracted their psychological traits from questionnaires, and social networks by conducting the survey on the nominating community members. We created a neural network-based model to integrate behavioral, psychological, and social network factors to predict mental health problems. The experimental results verify the efficacy of the proposed model, and demonstrate that the classification model of various factors effectively predicts the students' mental issues. © 2021 IEEE.
- Authors: Zhang, Dongyu , Guo, Teng , Han, Shiyu , Vahabli, Sadaf , Naseriparsa, Mehdi , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE International Conference on Big Data, Big Data 2021, virtual online, 15-18 December 2021, Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021 p. 4537-4546
- Full Text:
- Reviewed:
- Description: Mental health is an integral part of human health and well-being. Unhealthy mentality leads to serious consequences such as self-mutilation and suicide, especially for college students. While the literature focused on analysing the relationship between mental health and a single factor such as personality or behavior, accurate prediction is yet to be achieved due to the lack of cross-dimensional analysis and multi-dimensional joint prediction. To this end, this work proposes leveraging multiple factors from three crucial dimensions of mental health: behaviors, personality, and social networks. We recruited 490 college students, and collected their behavioral records from smart cards. In addition, we extracted their psychological traits from questionnaires, and social networks by conducting the survey on the nominating community members. We created a neural network-based model to integrate behavioral, psychological, and social network factors to predict mental health problems. The experimental results verify the efficacy of the proposed model, and demonstrate that the classification model of various factors effectively predicts the students' mental issues. © 2021 IEEE.
MAM : a metaphor-based approach for mental illness detection
- Zhang, Dongyu, Shi, Nan, Peng, Ciyuan, Aziz, Abdul, Zhao, Wenhong, Xia, Feng
- Authors: Zhang, Dongyu , Shi, Nan , Peng, Ciyuan , Aziz, Abdul , Zhao, Wenhong , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 21st International Conference on Computational Science, ICCS 2021 Vol. 12744 LNCS, p. 570-583
- Full Text:
- Reviewed:
- Description: Among the most disabling disorders, mental illness is one that affects millions of people across the world. Although a great deal of research has been done to prevent mental disorders, detecting mental illness in potential patients remains a considerable challenge. This paper proposes a novel metaphor-based approach (MAM) to determine whether a social media user has a mental disorder or not by classifying social media texts. We observe that the social media texts posted by people with mental illness often contain many implicit emotions that metaphors can express. Therefore, we extract these texts’ metaphor features as the primary indicator for the text classification task. Our approach firstly proposes a CNN-RNN (Convolution Neural Network - Recurrent Neural Network) framework to enable the representations of long texts. The metaphor features are then applied to the attention mechanism for achieving the metaphorical emotions-based mental illness detection. Subsequently, compared with other works, our approach achieves creative results in the detection of mental illnesses. The recall scores of MAM on depression, anorexia, and suicide detection are the highest, with 0.50, 0.70, and 0.65, respectively. Furthermore, MAM has the best F1 scores on depression and anorexia detection tasks, with 0.51 and 0.71. © 2021, Springer Nature Switzerland AG.
- Authors: Zhang, Dongyu , Shi, Nan , Peng, Ciyuan , Aziz, Abdul , Zhao, Wenhong , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 21st International Conference on Computational Science, ICCS 2021 Vol. 12744 LNCS, p. 570-583
- Full Text:
- Reviewed:
- Description: Among the most disabling disorders, mental illness is one that affects millions of people across the world. Although a great deal of research has been done to prevent mental disorders, detecting mental illness in potential patients remains a considerable challenge. This paper proposes a novel metaphor-based approach (MAM) to determine whether a social media user has a mental disorder or not by classifying social media texts. We observe that the social media texts posted by people with mental illness often contain many implicit emotions that metaphors can express. Therefore, we extract these texts’ metaphor features as the primary indicator for the text classification task. Our approach firstly proposes a CNN-RNN (Convolution Neural Network - Recurrent Neural Network) framework to enable the representations of long texts. The metaphor features are then applied to the attention mechanism for achieving the metaphorical emotions-based mental illness detection. Subsequently, compared with other works, our approach achieves creative results in the detection of mental illnesses. The recall scores of MAM on depression, anorexia, and suicide detection are the highest, with 0.50, 0.70, and 0.65, respectively. Furthermore, MAM has the best F1 scores on depression and anorexia detection tasks, with 0.51 and 0.71. © 2021, Springer Nature Switzerland AG.
Expressing metaphorically, writing creatively: Metaphor identification for creativity assessment
- Zhang, Dongyu, Zhang, Minghao, Peng, Ciyuan, Xia, Feng
- Authors: Zhang, Dongyu , Zhang, Minghao , Peng, Ciyuan , Xia, Feng
- Date: 2022
- Type: Text , Conference proceedings
- Relation: WWW '22: Companion Proceedings of the Web Conference , Virtual event , April 2022 p. 1198-
- Full Text:
- Reviewed:
- Description: Metaphor, which can implicitly express profound meanings and emotions, is a unique writing technique frequently used in human language. In writing, meaningful metaphorical expressions can enhance the literariness and creativity of texts. Therefore, the usage of metaphor is a significant impact factor when assessing the creativity and literariness of writing. However, little to no automatic writing assessment system considers metaphorical expressions when giving the score of creativity. For improving the accuracy of automatic writing assessment, this paper proposes a novel creativity assessment model that imports a token-level metaphor identification method to extract metaphors as the indicators for creativity scoring. The experimental results show that our model can accurately assess the creativity of different texts with precise metaphor identification. To the best of our knowledge, we are the first to apply automatic metaphor identification to assess writing creativity. Moreover, identifying features (e.g., metaphors) that influence writing creativity using computational approaches can offer fair and reliable assessment methods for educational settings.
- Authors: Zhang, Dongyu , Zhang, Minghao , Peng, Ciyuan , Xia, Feng
- Date: 2022
- Type: Text , Conference proceedings
- Relation: WWW '22: Companion Proceedings of the Web Conference , Virtual event , April 2022 p. 1198-
- Full Text:
- Reviewed:
- Description: Metaphor, which can implicitly express profound meanings and emotions, is a unique writing technique frequently used in human language. In writing, meaningful metaphorical expressions can enhance the literariness and creativity of texts. Therefore, the usage of metaphor is a significant impact factor when assessing the creativity and literariness of writing. However, little to no automatic writing assessment system considers metaphorical expressions when giving the score of creativity. For improving the accuracy of automatic writing assessment, this paper proposes a novel creativity assessment model that imports a token-level metaphor identification method to extract metaphors as the indicators for creativity scoring. The experimental results show that our model can accurately assess the creativity of different texts with precise metaphor identification. To the best of our knowledge, we are the first to apply automatic metaphor identification to assess writing creativity. Moreover, identifying features (e.g., metaphors) that influence writing creativity using computational approaches can offer fair and reliable assessment methods for educational settings.
The effect of facial perception and academic performance on social centrality
- Zhang, Dongyu, Peng, Ciyuan, Chang, Xiaojun, Xia, Feng
- Authors: Zhang, Dongyu , Peng, Ciyuan , Chang, Xiaojun , Xia, Feng
- Date: 2023
- Type: Text , Journal article
- Relation: IEEE Transactions on Computational Social Systems Vol. 10, no. 3 (2023), p. 970-981
- Full Text: false
- Reviewed:
- Description: Facial perception is of significant influence on the positions of people in social networks. Particularly, students' facial traits can affect their social centrality in educational settings (e.g., students looking intelligent can attract more friends). However, in educational environments, the social biases associated with appearances have alarming consequences, and little research has been done to investigate the effect of facial perception on social networks. Therefore, it is necessary to comprehensively analyze the influence of perceived facial traits on students' status in social interaction. In this article, we explore the effect of facial perception on the social centrality of students in social networks. Because students' social centrality is based on both their study ability and facial traits, this study does a comparative analysis of how facial perception and academic performance influence the social centrality of students. Subsequently, the experimental results demonstrate that facial perception, as well as academic performance, closely correlates with the social centrality of students. Finally, this study contributes to a comprehensive and deep understanding of social networks by analyzing facial trait-based social biases. © 2014 IEEE.
In your face : sentiment analysis of metaphor with facial expressive features
- Zhang, Dongyu, Zhang, Minghao, Guo, Teng, Peng, Ciyuan, Saikrishna, Vidya, Xia, Feng
- Authors: Zhang, Dongyu , Zhang, Minghao , Guo, Teng , Peng, Ciyuan , Saikrishna, Vidya , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 International Joint Conference on Neural Networks, IJCNN 2021 Vol. 2021-July
- Full Text:
- Reviewed:
- Description: Metaphor plays an important role in human communication, which often conveys and evokes sentiments. Numerous approaches to sentiment analysis of metaphors have thus gained attention in natural language processing (NLP). The primary focus of these approaches is on linguistic features and text rather than other modal information and data. However, visual features such as facial expressions also play an important role in expressing sentiments. In this paper, we present a novel neural network approach to sentiment analysis of metaphorical expressions that combines both linguistic and visual features and refer to it as the multimodal model approach. For this, we create a Chinese dataset, containing textual data from metaphorical sentences along with visual data on synchronized facial images. The experimental results indicate that our multimodal model outperforms several other linguistic and visual models, and also outperforms the state-of-the-art methods. The contribution is realized in terms of novelty of the approach and creation of a new, sizeable, and scarce dataset with linguistic and synchronized facial expressive image data. The dataset is particularly useful in languages other than English and the approach addresses one of the most challenging NLP issue: sentiment analysis in metaphor. © 2021 IEEE.
- Authors: Zhang, Dongyu , Zhang, Minghao , Guo, Teng , Peng, Ciyuan , Saikrishna, Vidya , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 International Joint Conference on Neural Networks, IJCNN 2021 Vol. 2021-July
- Full Text:
- Reviewed:
- Description: Metaphor plays an important role in human communication, which often conveys and evokes sentiments. Numerous approaches to sentiment analysis of metaphors have thus gained attention in natural language processing (NLP). The primary focus of these approaches is on linguistic features and text rather than other modal information and data. However, visual features such as facial expressions also play an important role in expressing sentiments. In this paper, we present a novel neural network approach to sentiment analysis of metaphorical expressions that combines both linguistic and visual features and refer to it as the multimodal model approach. For this, we create a Chinese dataset, containing textual data from metaphorical sentences along with visual data on synchronized facial images. The experimental results indicate that our multimodal model outperforms several other linguistic and visual models, and also outperforms the state-of-the-art methods. The contribution is realized in terms of novelty of the approach and creation of a new, sizeable, and scarce dataset with linguistic and synchronized facial expressive image data. The dataset is particularly useful in languages other than English and the approach addresses one of the most challenging NLP issue: sentiment analysis in metaphor. © 2021 IEEE.
- «
- ‹
- 1
- ›
- »