Knowledge-enriched joint-learning model for implicit emotion cause extraction

Emotion cause extraction(ECE)task that aims at extracting potential trigger events of certain emotions has attracted extensive attention recently.However,current work neglects the implicit emotion expressed without any explicit emotional keywords,which appears more frequently in application scenarios.The lack of explicit emotion information makes it extremely hard to extract emotion causes only with the local context.Moreover,an entire event is usually across multiple clauses,while existing work merely extracts cause events at clause level and cannot effectively capture complete cause event information.To address these issues,the events are first redefined at the tuple level and a span-based tuple-level algorithm is proposed to extract events from different clauses.Based on it,a corpus for implicit emotion cause extraction that tries to extract causes of implicit emotions is constructed.The authors propose a knowledge-enriched jointlearning model of implicit emotion recognition and implicit emotion cause extraction tasks(KJ-IECE),which leverages commonsense knowledge from ConceptNet and NRC_VAD to better capture connections between emotion and corresponding cause events.Experiments on both implicit and explicit emotion cause extraction datasets demonstrate the effectiveness of the proposed model.

A Method of Multimodal Emotion Recognition in Video Learning Based on Knowledge Enhancement

With the popularity of online learning and due to the significant influence of emotion on the learning effect,more and more researches focus on emotion recognition in online learning.Most of the current research uses the comments of the learning platform or the learner’s expression for emotion recognition.The research data on other modalities are scarce.Most of the studies also ignore the impact of instructional videos on learners and the guidance of knowledge on data.Because of the need for other modal research data,we construct a synchronous multimodal data set for analyzing learners’emotional states in online learning scenarios.The data set recorded the eye movement data and photoplethysmography(PPG)signals of 68 subjects and the instructional video they watched.For the problem of ignoring the instructional videos on learners and ignoring the knowledge,a multimodal emotion recognition method in video learning based on knowledge enhancement is proposed.This method uses the knowledge-based features extracted from instructional videos,such as brightness,hue,saturation,the videos’clickthrough rate,and emotion generation time,to guide the emotion recognition process of physiological signals.This method uses Convolutional Neural Networks(CNN)and Long Short-Term Memory(LSTM)networks to extract deeper emotional representation and spatiotemporal information from shallow features.The model uses multi-head attention(MHA)mechanism to obtain critical information in the extracted deep features.Then,Temporal Convolutional Network(TCN)is used to learn the information in the deep features and knowledge-based features.Knowledge-based features are used to supplement and enhance the deep features of physiological signals.Finally,the fully connected layer is used for emotion recognition,and the recognition accuracy reaches 97.51%.Compared with two recent researches,the accuracy improved by 8.57%and 2.11%,respectively.On the four public data sets,our proposed method also achieves better results compared with the two recent researches.The experiment results show that the proposed multimodal emotion recognition method based on knowledge enhancement has good performance and robustness.

Effect of emotion management and nursing on patients with painless induced abortion after operation

BACKGROUND With an estimated 121 million abortions following unwanted pregnancies occurring worldwide each year,many countries are now committed to protecting women’s reproductive rights.AIM To analyze the impact of emotional management and care on anxiety and contraceptive knowledge mastery in painless induced abortion(IA)patients.METHODS This study was retrospective analysis of 84 patients with IA at our hospital.According to different nursing methods,the patients were divided into a control group and an observation group,with 42 cases in each group.Degree of pain,rate of postoperative uterine relaxation,surgical bleeding volume,and postoperative bleeding volume at 1 h between the two groups of patients;nursing satisfaction;and mastery of contraceptive knowledge were analyzed.RESULTS After nursing,Self-Assessment Scale,Depression Self-Assessment Scale,and Hamilton Anxiety Scale scores were 39.18±2.18,30.27±2.64,6.69±2.15,respectively,vs 45.63±2.66,38.61±2.17,13.45±2.12,respectively,with the observation group being lower than the control group(P<0.05).Comparing visual analog scales,the observation group was lower than the control group(4.55±0.22 vs 3.23±0.41;P<0.05).The relaxation rate of the cervix after nursing,surgical bleeding volume,and 1-h postoperative bleeding volumes were 25(59.5),31.72±2.23,and 22.41±1.23,respectively,vs 36(85.7),42.39±3.53,28.51±3.34,respec tively,for the observation group compared to the control group.The observation group had a better nursing situation(P<0.05),and higher nursing satisfaction and contraceptive knowledge mastery scores compared to the control group(P<0.05).CONCLUSION The application of emotional management in postoperative care of IA has an ideal effect.

Reasoning about Epistemic Actions and Knowledge in Multi-Agent Systems Using Coq

In this paper, the authors outline a formal system for reasoning about agents＇ knowledge in knowledge games-a special type of multi-agent system. Knowledge games are card games where the agents＇ actions involve an exchange of information with other agents in the game. The authors＇ system is modeled using Coq-a formal proof management system. To the best of the authors＂ knowledge, there are no papers in which knowledge games are considered using a Coq proof assistant. The authors use the dynamic logic of common knowledge, where they particularly focus on the epistemic consequences of epistemic actions carried out by agents. The authors observe the changes in the system that result from such actions. Those changes that can occur in such a system that are of interest to the authors take the form of agents＇ knowledge about the state of the system, knowledge about other agents＇ knowledge, higher-order agents＇ knowledge and so on, up to common knowledge. Besides an axiomatic ofepistemic logic, the authors use a known axiomatization of card games that is extended with some new axioms that are required for the authors＇ approach. Due to a deficit in implementations grounded in theory that enable players to compute their knowledge in any state of the game, the authors show how the authors＇ approach can be used for these purposes.

Traditional agroecological knowledge and practices:The drivers and opportunities for adaptation actions in the northern region of Ghana

Agroecological practices are promoted as a more proactive approach than conventional agriculture to achieving a collective global response to climate change and variability while building robust and resilient agricultural systems to meet food needs and protect the integrity of ecosystems.There is relatively limited evidence on the key traditional agroecological knowledge and practices adopted by smallholder farmers,the factors that influence smallholder farmers’decision to adopt these practices,and the opportunities it presents for building resilient agricultural systems.Using a multi-scale mixed method approach,we conducted key informant interviews(n=12),focus group discussions(n=5),and questionnaire surveys(N=220)to explore the traditional agroecological knowledge and practices,the influencing factors,and the opportunities smallholder farmers presented for achieving resilient agricultural systems.Our findings suggest that smallholder farmers employ a suite of traditional agroecological knowledge and practices to enhance food security,combat climate change,and build resilient agricultural systems.The most important traditional agroecological knowledge and practices in the study area comprise cultivating leguminous crops,mixed crop-livestock systems,and crop rotation,with Relative Importance Index(RII)values of 0.710,0.708,and 0.695,respectively.It is reported that the choice of these practices by smallholder farmers is influenced by their own farming experience,access to market,access to local resources,information,and expertise,and the perceived risk of climate change.Moreover,the results further show that improving household food security and nutrition,improving soil quality,control of pest and disease infestation,and support from NonGovernmental Organizations(NGOs)and local authorities are opportunities for smallholder farmers in adopting traditional agroecological knowledge and practices for achieving resilient agricultural systems.The findings call into question the need for stakeholders and policy-makers at all levels to develop capacity and increase the awareness of traditional agroecological knowledge and practices as mechanisms to ensure resilient agricultural systems for sustainable food security.

Decision Tree and Naive Bayes Algorithm for Classification and Generation of Actionable Knowledge for Direct Marketing

Many companies like credit card, insurance, bank, retail industry require direct marketing. Data mining can help those institutes to set marketing goal. Data mining techniques have good prospects in their target audiences and improve the likelihood of response. In this work we have investigated two data mining techniques: the Naive Bayes and the C4.5 decision tree algorithms. The goal of this work is to predict whether a client will subscribe a term deposit. We also made comparative study of performance of those two algorithms. Publicly available UCI data is used to train and test the performance of the algorithms. Besides, we extract actionable knowledge from decision tree that focuses to take interesting and important decision in business area.

Agglomerative Approach for Identification and Elimination of Web Robots from Web Server Logs to Extract Knowledge about Actual Visitors

In this paper we investigate the effectiveness of ensemble-based learners for web robot session identification from web server logs. We also perform multi fold robot session labeling to improve the performance of learner. We conduct a comparative study for various ensemble methods (Bagging, Boosting, and Voting) with simple classifiers in perspective of classification. We also evaluate the effectiveness of these classifiers (both ensemble and simple) on five different data sets of varying session length. Presently the results of web server log analyzers are not very much reliable because the input log files are highly inflated by sessions of automated web traverse software’s, known as web robots. Presence of web robots access traffic entries in web server log repositories imposes a great challenge to extract any actionable and usable knowledge about browsing behavior of actual visitors. So web robots sessions need accurate and fast detection from web server log repositories to extract knowledge about genuine visitors and to produce correct results of log analyzers.

Multi-action-based approach for constructing knowledge map

To alleviate the information overload in the product design process,this work proposes a multiaction-based method for constructing knowledge map. Since the relationships of knowledge are implicit in the collected user activities,the method calculates the similarity according to the collected user activities.Three concepts,including knowledge,action and user,are explained first. Based on this,the similarity calculation method is illustrated in detail. The dependencies of actions and relations of the user are considered in the calculation method. Further,the approach of applying the constructed knowledge map to alleviate information overload is proposed. At last,the proposed method is validated by a knowledge search and result comparison experiment.

Is Knowledge Power?

Francis Bacon’s famous quote“knowledge is power,”has long been misunderstood,for his real intention was precisely to make humankind aware of the limitations of knowledge.His concept of potestas(power)is not about conquest,but about action,aiming to clarify the nature of knowledge,to get rid of the empty and shallow contemplation of antiquity,and thus to bring the spirit of the real world back to the earth,as Socrates did.Bacon emphasized the unity of knowledge and action while valuing action over knowledge.Nature in Bacon’s time was no longer sacred and was degraded to a poor substance that revealed its secrets after being tortured by scientific technology.As a result,natural teleology was completely abandoned.Bacon put man in increasing tension with nature,heralding Kant’s argument that human reason prescribed lawfulness to nature.But Bacon,after all,lived in an era not far from antiquity,so he agreed the limitations of knowledge and action and considered technology to be a labyrinth prone to divest one’s identity.Bacon thought that knowledge could be venom that made humankind swell,and the antidote was charity.Bacon’s quote is not so much an encouragement to take from nature as it is a way to learn from nature and to take a practical approach to happiness.

EP-Bot: Empathetic Chatbot Using Auto-Growing Knowledge Graph

People occasionally interact with each other through conversation.In particular,we communicate through dialogue and exchange emotions and information from it.Emotions are essential characteristics of natural language.Conversational artificial intelligence is an integral part of all the technologies that allow computers to communicate like humans.For a computer to interact like a human being,it must understand the emotions inherent in the conversation and generate the appropriate responses.However,existing dialogue systems focus only on improving the quality of understanding natural language or generating natural language,excluding emotions.We propose a chatbot based on emotion,which is an essential element in conversation.EP-Bot(an Empathetic PolarisX-based chatbot)is an empathetic chatbot that can better understand a person’s utterance by utilizing PolarisX,an autogrowing knowledge graph.PolarisX extracts new relationship information and expands the knowledge graph automatically.It is helpful for computers to understand a person’s common sense.The proposed EP-Bot extracts knowledge graph embedding using PolarisX and detects emotion and dialog act from the utterance.Then it generates the next utterance using the embeddings.EP-Bot could understand and create a conversation,including the person’s common sense,emotion,and intention.We verify the novelty and accuracy of EP-Bot through the experiments.

The mediating role of environmental emotions in transition from knowledge to sustainable use of groundwater resources in Iran's agriculture

The excessive use of groundwater resources has created numerous environmental consequences in Iran. Many water experts believe that this crisis can be overcome by fostering sustainable environmental behavior in the utilization of groundwater resources and increasing the farmers' environmental knowledge, attitude and emotions. The objective of this study was to investigate transformation of en-vironmental knowledge to sustainable use of groundwater resources through the analysis of the med-iating role of environmental emotions in Iran's agriculture. This research was carried out via a survey technique within the category of descriptive-correlation and causal-relational research. All the wheat producing farmers of Sistan and Baluchestan Province, which is a clear example of critical conditions for groundwater resources in Iran (N=168,873), constituted the statistical population of the study of whom 384 participants were selected using a stratified random sampling method. The research instrument was a questionnaire whose validity was confirmed by a panel of professionals in agricultural extension, education and water management. The reliability of the items of the questionnaire was also evaluated via a pilot study and Cronbach's alpha (0.70≤α≤0.84). The results of the causal analysis indicated that environmental knowledge (β=0.309) and environmental emotions (β=0.565) have the significant in-fluence on sustainable environmental behavior in the utilization of groundwater among wheat farmers. Therefore, it can be said environmental emotions is an important mediating factor for potentially im-proving water stakeholders' sustainable environmental behavior.

A discussion of the emotive element of knowledge service practice:An empirical study at the Chinese Academy of Sciences

With the arrival of the information age, research activities focused on the practice and approaches of knowledge services are on a marked increase as evidenced in the publications of social sciences. According to a social network analysis on knowledge service related literature, it reveals that information and knowledge workers often fail to take such an important element as the functional role of an emotive engagement into consideration in their study of knowledge services. It has increasingly become an issue of high profile with the rapid development of digital libraries and their web-based knowledge services in China and anywhere else in the world. In order to have a clearer understanding about issues involved in knowledge servicing so as to maximize the effectiveness and efficiency of digital libraries in their knowledge service performance, the author has conducted surveys for seven times on the online information seeking behavior of graduate students at the Chinese Academy of Sciences with such research methods as questionnaires, interviews and natural observations during September 2006-June 2009. The research result has showed the emotive element has an important role in the user's information seeking behavior and in knowledge services practice. Therefore, knowledge services rendered may be more effective by adding the emotiveness-oriented communication element into such practice. This paper recommends that such an emotiveness-oriented communication approach should be carefully studied and factored into libraries' knowledge services practice.

TwinNet: Twin Structured Knowledge Transfer Network for Weakly Supervised Action Localization

Action recognition and localization in untrimmed videos is important for many applications and have attracted a lot of attention. Since full supervision with frame-level annotation places an overwhelming burden on manual labeling effort, learning with weak video-level supervision becomes a potential solution. In this paper, we propose a novel weakly supervised framework to recognize actions and locate the corresponding frames in untrimmed videos simultaneously. Considering that there are abundant trimmed videos publicly available and well-segmented with semantic descriptions, the instructive knowledge learned on trimmed videos can be fully leveraged to analyze untrimmed videos. We present an effective knowledge transfer strategy based on inter-class semantic relevance. We also take advantage of the self-attention mechanism to obtain a compact video representation, such that the influence of background frames can be effectively eliminated. A learning architecture is designed with twin networks for trimmed and untrimmed videos, to facilitate transferable self-attentive representation learning. Extensive experiments are conducted on three untrimmed benchmark datasets (i.e., THUMOS14, ActivityNet1.3, and MEXaction2), and the experimental results clearly corroborate the efficacy of our method. It is especially encouraging to see that the proposed weakly supervised method even achieves comparable results to some fully supervised methods.

基于层级图卷积网络的情绪识别模型

细粒度情绪识别模型采用比传统方法更多的情绪类别,能更为准确地捕捉人们日常生活中经历和表达的情绪。然而,大幅增加的情绪类别以及细粒度情绪间存在的相互关联和模糊性,给细粒度情绪识别模型带来了挑战。已有情绪识别工作表明,引入情感词典等外部知识可以有效提升模型性能。但现有细粒度情绪识别模型引入情感知识的方式还较为简单,仍未考虑深层情感知识,例如,情感层级关系。针对上述问题,该文提出一种基于层级图卷积网络的情绪识别(Hierarchy Graph Convolution Networks-based Emotion Recognition,HGCN-EC)模型。HGCN-EC模型由语义信息模块、情绪层级结构知识模块和知识融合模块组成。语义信息模块提取文本的语义特征;情绪层级结构知识模块将细粒度情绪构建为树状层级结构并使用贝叶斯统计推断计算情绪之间的转移概率作为层级知识;知识融合模块采用图卷积网络将情绪层级知识与文本语义特征融合,用于实现情绪预测。在GoEmotions数据集上的对比实验结果表明,HGCN-EC模型具有相较于基线方法更优的细粒度情绪识别性能。

基于知识图谱的多特征融合谣言检测方法

为了解决谣言检测中由于缺乏外部知识而导致模型难以感知内隐信息,进而限制了模型挖掘深层信息的能力这个问题,提出了基于知识图谱的多特征融合谣言检测方法(KGMRD)。首先,对于每个事件,将帖子和评论共同构建为一个文本序列,并利用分类器从中提取情感特征,利用ConceptNet基于文本构造其知识图谱,将知识图谱中的实体表示利用注意力机制与文本的语义特征进行聚合,进而得到增强的语义特征表示;其次,在传播结构方面,对于每个事件,基于帖子的传播转发关系构建传播结构图,使用DropEdge对传播结构图进行剪枝,从而得到更有效的传播结构特征;最后,将得到的特征进行融合处理得到一个新的表示。在Weibo、Twitter15和Twitter16三个真实数据集上,使用SVM-RBF等七个模型作为基线进行了对比实验。结果表明:对比当前效果最好的基线,KGMRD方法在Weibo数据集的ACC指标提升了1.1%;在Twitter15和Twitter16数据集的ACC指标上提升了2.2%,证明了KGMRD方法是合理的、有效的。

差异化授权型领导与知识型员工知识隐藏——基于跨层分析

基于团队和个体视角构建两个中介模型,探讨差异化授权型领导对知识型员工知识隐藏的内在作用机制。通过对67个团队的358位员工进行跨层检验,分析发现:在团队层面,差异化授权型领导通过降低团队信任,从而增强知识型员工知识隐藏动机;在个体层面,差异化授权型领导通过对知识型员工角色负荷、情绪耗竭的链式影响而诱发知识隐藏行为。上述结论丰富了差异化授权型领导影响后果研究,为促进团队成员知识分享与流动提供了重要的实践启示。

课程思政背景下大学英语教师教学评价素养探析

课程思政背景下的大学英语教师教学评价素养结构就是由三维度(素养、评价、教学)、六要素(评价情感、评价知识、评价技能、评价阶段、评价反思和评价监督)构成分层次的立体结构。英语教师思政教学评价素养的发展就是教师的评价知识、评价技能及评价情感通过内在的评价反思,以及外在的评价监管在课前、课中、课后不断发展、达到动态平衡的过程。要提高大学英语教师评价素养,教师自身应反思大学英语思政课堂评价质量,提高教学评价效果;学校形成评价监督机制,规范教师评价行为,并为教师提供评价实践机会,提高教师评价实践能力。

阳明心学中的道德知识与道德动机——从“良知发用”的角度看

基于比较哲学视野的分析,王阳明的知行合一论题的解释在传统中包含着三种不同路径的理解,即形而上学论题、知识论论题和元伦理学论题。致良知学说体现了知行合一的三种路径理解的统一,其中道德知识和道德动机的关系是把握知行合一与致良知学说的关键。本文把心学工夫论理解为道德意识的自我展开和实现,通过论证良知发用的功能,阐明阳明心学中包含着近似于内在主义道德动机的混合模型,并由此产生奠基于道德感知和道德情感交互性的美德伦理论述。