Analysis of community question-answering issues via machine learning and deep learning:State-of-the-art review

Over the last couple of decades,community question-answering sites(CQAs)have been a topic of much academic interest.Scholars have often leveraged traditional machine learning(ML)and deep learning(DL)to explore the ever-growing volume of content that CQAs engender.To clarify the current state of the CQA literature that has used ML and DL,this paper reports a systematic literature review.The goal is to summarise and synthesise the major themes of CQA research related to(i)questions,(ii)answers and(iii)users.The final review included 133 articles.Dominant research themes include question quality,answer quality,and expert identification.In terms of dataset,some of the most widely studied platforms include Yahoo!Answers,Stack Exchange and Stack Overflow.The scope of most articles was confined to just one platform with few cross-platform investigations.Articles with ML outnumber those with DL.Nonetheless,the use of DL in CQA research is on an upward trajectory.A number of research directions are proposed.

Expert Recommendation in Community Question Answering via Heterogeneous Content Network Embedding

ExpertRecommendation(ER)aims to identify domain experts with high expertise and willingness to provide answers to questions in Community Question Answering(CQA)web services.How to model questions and users in the heterogeneous content network is critical to this task.Most traditional methods focus on modeling questions and users based on the textual content left in the community while ignoring the structural properties of heterogeneous CQA networks and always suffering from textual data sparsity issues.Recent approaches take advantage of structural proximities between nodes and attempt to fuse the textual content of nodes for modeling.However,they often fail to distinguish the nodes’personalized preferences and only consider the textual content of a part of the nodes in network embedding learning,while ignoring the semantic relevance of nodes.In this paper,we propose a novel framework that jointly considers the structural proximity relations and textual semantic relevance to model users and questions more comprehensively.Specifically,we learn topology-based embeddings through a hierarchical attentive network learning strategy,in which the proximity information and the personalized preference of nodes are encoded and preserved.Meanwhile,we utilize the node’s textual content and the text correlation between adjacent nodes to build the content-based embedding through a meta-context-aware skip-gram model.In addition,the user’s relative answer quality is incorporated to promote the ranking performance.Experimental results show that our proposed framework consistently and significantly outperforms the state-of-the-art baselines on three real-world datasets by taking the deep semantic understanding and structural feature learning together.The performance of the proposed work is analyzed in terms of MRR,P@K,and MAP and is proven to be more advanced than the existing methodologies.

Answer Classification via Machine Learning in Community Question Answering

As a new type of knowledge sharing platform,the community question answer website realizes the acquisition and sharing of knowledge,and is loved and sought after by the majority of users.But for multi-answer questions,answer quality assessment becomes a challenge.The answer selection in CQA(Community Question Answer)was proposed as a challenge task in the SemEval competition,which gave a data set and proposed two subtasks.Task-A is to give a question(including short title and extended description)and its answers,and divide each answer into absolutely relevant(good),potentially relevant(potential)and bad or irrelevant(bad,dialog,non-English,other).Task-B is to give a YES/NO type question(including short title and extended description)and some answers.Based on the answer of the absolute correlation type(good),judge whether the answer to the whole question should be yes,no or uncertain.This paper first preprocesses this data set,and then uses natural language processing technology to perform word segmentation,part-of-speech tagging and named entity recognition on the data set,and then perform feature extraction on the preprocessed data set.Finally,SVM and random forest are used to classify on the basis of feature extraction,and the classification results are analyzed and compared.The experiments in this paper show that SVM and random forest methods have good results on the data set,and exceed the multi-classifier ensemble learning method and hierarchical classification method proposed by the predecessors.

ACLSTM:A Novel Method for CQA Answer Quality Prediction Based on Question-Answer Joint Learning

Given the limitations of the community question answering(CQA)answer quality prediction method in measuring the semantic information of the answer text,this paper proposes an answer quality prediction model based on the question-answer joint learning(ACLSTM).The attention mechanism is used to obtain the dependency relationship between the Question-and-Answer(Q&A)pairs.Convolutional Neural Network(CNN)and Long Short-term Memory Network(LSTM)are used to extract semantic features of Q&A pairs and calculate their matching degree.Besides,answer semantic representation is combined with other effective extended features as the input representation of the fully connected layer.Compared with other quality prediction models,the ACLSTM model can effectively improve the prediction effect of answer quality.In particular,the mediumquality answer prediction,and its prediction effect is improved after adding effective extended features.Experiments prove that after the ACLSTM model learning,the Q&A pairs can better measure the semantic match between each other,fully reflecting the model’s superior performance in the semantic information processing of the answer text.

A comparative analysis of major Chinese and English online question-answering communities

This paper compares 12 representative Chinese and English online questionanswering communities(Q&A communities) based on their basic functions, interactive modes, and customized services. An empirical experiment from a comparative perspective was also conducted on them by using 12 questions representing for four types of questions,which are assigned evenly to three different subject fields so as to examine the task performance of these 12 selected online Q&A communities. Our goal was to evaluate those online Q&A communities in terms of their quality and efficiency for answering questions posed to them. It was hoped that our empirical research would yield greater understanding and insights to the working intricacy of these online Q&A communities and hence their possible further improvement.

基于城乡差异的大学生成长与CQA平台关系调查

基于社区的在线问答平台(CQA)在大学生课堂内外的学习和实践中扮演着越来越重要的角色,但是不断扩大的城乡贫富差距使城市大学生和农村大学生已经异化为不同的群体,而这些群体对于CQA的态度和接受度是否存在差异还缺少相应的研究。已有一些调查文献证明CQA系统对大学生自身成长具有积极的效应。这种效应在城乡大学生之间是否存在差异?农村学生对于CQA平台的态度和认知与城市学生相比有哪些不同?一项基于技术接受模型和自我决定理论的问卷对此进行了调查。在偏最小二乘的结构方程模型的数据分析下发现:相比于城市学生,农村学生从CQA的改进中所获得的收益较少;而相比于有用性,CQA在易用性方面的改进对学生的能力成长有着更为显著地效果,尽管目前系统在易用性上的表现还差强人意。

A Survey on Expert Recommendation in Community Question Answering

Community question answering （CQA） represents the type of Web applications where people can exchange knowledge via asking and answering questions. One significant challenge of most real-world CQA systems is the lack of effective matching between questions and the potential good answerers, which adversely affects the efficient knowledge acquisition and circulation. On the one hand, a requester might experience many low-quality answers without receiving a quality response in a brief time; on the other hand, an answerer might face numerous new questions without being able to identify the questions of interest quickly. Under this situation, expert recommendation emerges as a promising technique to address the above issues. Instead of passively waiting for users to browse and find their questions of interest, an expert recommendation method raises the attention of users to the appropriate questions actively and promptly. The past few years have witnessed considerable efforts that address the expert recommendation problem from different perspectives. These methods all have their issues that need to be resolved before the advantages of expert recommendation can be fully embraced. In this survey, we first present an overview of the research efforts and state-of-the-art techniques for the expert recommendation in CQA. We next summarize and compare the existing methods concerning their advantages and shortcomings, followed by discussing the open issues and future research directions.

问答系统研究综述

近年来,问答系统被大量广泛地研究。问答系统的目标是给定一个问题,能够得到简短、精确的答案。根据处理数据的不同,将问答系统分为三类:基于结构化数据的问答系统、基于自由文本的问答系统、基于问题答案对的问答系统。对这三大类系统的特点、面临的问题和相关的研究分别进行了叙述和总结。最后,讨论了问答系统未来可能的研究方向。

面向问答社区的粗粒度问句分类算法

面向问答社区的问答系统CQA(Community Question Answer)是近年来研究的热点,针对系统中问句分类的复杂性,提出一个粗粒度的分类体系及多标记多分类的问句分类算法——MLMC。基于SVM分类模型实现一个完整的分类系统,总体分类精度达到73.6%。

社区问答网站中问题的刻面组织方法——以知乎网站为例

[目的/意义]社区问答(Community Question Answering,CQA)已成为当前主流的在线知识共享方式。目前,大多数CQA网站都采用了基于主题的问题组织方式。这类组织方式很难满足用户细粒度的问题检索与定位需求。[方法/过程]将主题的刻面(Facet)信息引入问题组织,提出了一种针对CQA网站中问题的刻面组织方法。该方法包括离线与在线两个过程,离线过程利用Wikipedia中的目录信息与相关主题间的刻面相似性生成特定主题的刻面结构;在线过程则利用迁移学习技术建立主题与刻面的映射关系。通过这两个过程,将问题组织成"主题-刻面-问题"层次结构。[结果 /结论]以知乎网站中"数据结构"领域相关知识主题的问题为对象进行了实验,验证了所提刻面组织方法的有效性。

基于关键信息的问题相似度计算

判断问题相似是社区问答(community question answer,CQA)中很重要的一个研究方向.社区问答中的问题通常由主题和描述构成.由于社区问答的开放性,用户的提问长短不一,而问题中会包含大量干扰模型判断问题是否相似的背景信息.为了减少上述问题对计算问题相似度的影响,模型将关键词及问题主题视为问题的关键信息,并使用这些信息计算问题相似度.首先,在基于文本间相似及相异信息的CNN模型的基础上引入了关键词抽取技术.同时,为了更好地利用问题主题的信息,模型融合了问题主题相似度的特征.模型在SemEval2017评测的问题相似任务中进行了实验,其平均精度均值(mean average precision,MAP)达到了49.65%,超过了评测中的最佳结果.

结合注意力与循环神经网络的专家推荐算法

在线问答社区(CQA)已经成为互联网最重要的知识分享交流平台,将用户提出的海量问题有效推荐给可能解答的用户,挖掘用户感兴趣的问题是此类平台最核心功能。一些针对问答社区的专家推荐算法已经被提出用来提高平台解答效率,但是现有工作大多关注于用户兴趣与问题信息匹配,忽视了用户兴趣动态变化问题,可能会严重影响推荐质量。提出了结合注意力与循环神经网络的专家推荐算法,不仅实现了问题信息的深度特征编码,而且还能捕获动态变化的用户兴趣。首先,问题编码器在预训练词嵌入基础上结合卷积神经网络(CNN)和Attention注意力机制实现了问题标题与绑定标签的深度特征联合表示。然后,用户编码器在用户历史回答问题的时间序列上利用长短期记忆神经网络Bi-GRU模型捕捉动态兴趣,并结合用户固定标签信息表征长期兴趣。最后,根据两个编码器输出向量的相似性计算产生用户动态兴趣与长期兴趣相结合的推荐结果。在来自知乎问答社区的真实数据上进行了不同参数配置及不同算法的对比实验,结果表明该算法性能明显优于目前比较流行的深度学习专家推荐算法。

面向问答社区的中文问题分类

传统的问题分类体系大都基于事实类问题,传统的问题分类方法也比较依赖于疑问词这一分类特征,但问答社区(CQA)中非事实类问题居多,且许多问题并不包含疑问词,为此,提出一种面向问答社区的粗粒度分类体系,并在此基础上提出一种基于疑问词的层次化结构问题分类方法。该方法首先自动识别问题中的疑问词,若疑问词存在,则用支持向量机(SVM)模型进行分类;而对没有疑问词的问题,则用所构造的基于焦点词的分类器进行分类。通过在从中文问答社区知乎中所爬取的问题数据集上进行实验,与传统的基于SVM模型的分类方法相比,该方法的分类准确率提高了4.7个百分点。实验结果表明,这种根据问题是否含有疑问词而选择不同分类器的方法,减轻了分类方法对疑问词的依赖,能有效提高问答社区中问题分类的准确率。

基于用户-标签异构网络的社区问答专家发现方法

在Stack Overflow、Quora等社区问答网站中,日益增长的用户数使新问题数量急剧增加,传统的专家发现方法通常根据历史回答记录建立用户文档,再从中提取用户文本特征,难以及时寻找到合适的专家进行回答。针对该问题,提出一种社区问答中基于用户-标签异构网络的专家发现方法。根据用户历史回答记录和问题的附带标签构建用户-标签网络,以此得到用户的向量表示。在此基础上,使用全连接神经网络提取用户特征和问题文本特征,通过比较两者的余弦相似度得到候选专家列表。基于StackExchange的真实世界数据集进行测试,实验结果表明,与LDA、STM、RankingSVM和QR-DSSM方法相比,该方法的MRR指标值较高,能够准确寻找到可提供正确答案的专家。

Answering contextual questions based on ontologies and question templates

上下文的问答(CQA ) ，在哪个用户信息需要通过交互问答(质量保证) 满足对话，最近吸引了更多的研究注意。一挑战是熔化上下文的信息进相关问题的理解的过程。在这篇论文，讲话结构被建议维持语义信息，并且来临因为关联类型和上下文的信息的熔化的识别根据关联类型被建议。系统在真实上下文的质量保证数据上被评估。结果证明更好的性能比一个基线系统并且几乎被完成这些上下文的现象什么时候手工地被解决的一样的表演。详细评估分析被介绍。

Understanding the factors influencing user intention to continue contributing knowledge in social Q&A communities

Purpose:A social question & answer(SQA) community's long-term sustainability depends on its members' willingness to stay and contribute their knowledge continuously in the community.This research aims to investigate the critical factors which influence users' intention to continue contributing knowledge in the SQA community.Design/methodology/approach:Grounded on information systems(IS) continuance theory,this study put forward a model of the factors that influence SQA community members' intention to continue contributing knowledge.Survey was conducted to gather data from knowledge contributors of four major Chinese SQA communities(Baidu Knows,Sina iAsk,Soso Ask and Yahoo! Knowledge).By using the partial least squares(PLS) technique,research hypotheses derived from the proposed model were empirically validated.Findings:Except enjoyment in helping others and knowledge self-efficacy,all other factors including extrinsic reward,reputation enhancement,realization of self-worth,perceived usefulness,attitude towards knowledge contribution,and satisfaction exert significant impacts on users' continuance intentions in an SQA community.Research limitations:First,important factors such as the ease of use of information systems which may influence users' continuance intentions were not investigated in the study.Second,the study sample needs to be enlarged,and users of smaller SQA communities should also be included,to make the results more representative.Practical implications:This study will help SQA community designers and managers develop or improve incentive mechanisms to attract more people to contribute their knowledge and promote the development of the SQA community.Originality/value:This study improves the previous research models and puts forward a model of user continuance intention to contribute knowledge in an SQA community.It will extend the understanding of SQA community users' intention to continue contributing knowledge by distinguishing these users' different roles and focusing only on knowledge contributors.

Enhanced Answer Selection in CQA Using Multi-Dimensional Features Combination

Community Question Answering(CQA) in web forums, as a classic forum for user communication,provides a large number of high-quality useful answers in comparison with traditional question answering.Development of methods to get good, honest answers according to user questions is a challenging task in natural language processing. Many answers are not associated with the actual problem or shift the subjects,and this usually occurs in relatively long answers. In this paper, we enhance answer selection in CQA using multidimensional feature combination and similarity order. We make full use of the information in answers to questions to determine the similarity between questions and answers, and use the text-based description of the answer to determine whether it is a reasonable one. Our work includes two subtasks:(a) classifying answers as good, bad, or potentially associated with a question, and(b) answering YES/NO based on a list of all answers to a question. The experimental results show that our approach is significantly more efficient than the baseline model, and its overall ranking is relatively high in comparison with that of other models.