Community Question Answering Research Articles

Klasterisasi Penjawab Berdasar Kualitas Jawaban pada Platform Brainly Menggunakan K-Means

Brainly is a Community Question Answering (CQA) educational platform that makes it easy for users to find answers based on questions posed by students. Questions from students are often answered quickly by many answerers interested in the field being asked. The number of available answers is the choice of students to be able to receive answers and give a good rating to the answerer. Based on the number of good ratings, an answerer can be said to be an expert in certain subjects. Therefore, this research focuses on finding expert answering groups who have quality answers. K-means clustering is possible to group the answering data into two different clusters. The first cluster is expert users with ten respondents, and The second cluster is a non-expert cluster with 474 respondents. The expert cluster data is expected to help the questioner to be able to ask questions directly to the experts and obtain quality answers. Meanwhile, the number of clusters is determined based on the test results using a silhouette score that obtains a value of 0.971, with the optimal number of clusters being two clusters.

EXPERT RECOMMENDATION THROUGH TAG RELATIONSHIP IN COMMUNITY QUESTION ANSWERING

Community Question Answering (CQA) services are technical discussion forums websites on social media that serve as a platform for users to interact mainly via question and answer. However, users of this platform have posed dissatisfaction over the slow response and the preference for user domains due to the overwhelming information in CQA websites. Numerous past studies focusing on expert recommendation are solely based on the information available from websites where they rarely account for the preference of users’ domain knowledge. This condition prompts the need to identify experts for the questions posted on community-based websites. Thus, this study attempts to identify ranking experts’ derived from the tag relationship among users in the CQA websites to construct user profiles where their interests are realized in the form of tags. Experts are considered users who post high-quality answers and are often recommended by the system based on their previous posts and associated tags. These associations further describe tags that often co-occur in posts and the significant domains of user interest. The current study further explores this relationship by adopting the “Tag Relationship Expert Recommendation (TRER)” method where Questions Answer (QA) Space is utilized as a dataset to identify users with similar interests and subsequently rank experts based on the tag-tag relationship for user’s question. The results show that the TRER method outperforms existing baseline methods by effectively improving the performance of relevant domain experts in CQA, thereby facilitating the expert recommendation process in answering questions posted by technical and academic professionals.

Heterogeneous graph prompt for Community Question Answering

SummaryCompared with general question answering, Community Question Answering (CQA), which has been widely used in various scenarios like E‐commerce and is well welcomed. In order to answer the user's question precisely, many CQA models resort to external knowledge sources such as Wikipedia. The main challenge of the task is knowledge extraction and utilization. Different from the traditional method of designing task‐specific knowledge modules, we propose a graph prompt‐based learning method that directly steers the pretrained language model to solve CQA tasks. Multiple information sources are organized as graph prompts to guide the generation of the model, naturally leveraging the knowledge learned in the pretrained step. Based on the pretrained bidirectional and autoregressive transformers, a large‐scale language model, a comparable performance is achieved with less than 10% of the full‐finetuning time by only optimizing the graph prompt parameters. Experiments on two standard CQA datasets show that compared with traditional sequential initialized prompts, graph prompt achieves 20.47% and 14.89% increments in terms of BLEU and ROUGE‐L scores on quick finetuning and outperforms in few‐shot learning.

Jacinda Ardern and the limits of gender on the Chinese-language Internet: a critical discourse analysis

ABSTRACT This article explores Chinese Internet users’ discussions about Jacinda Ardern’s maternity leave in the wake of her being elected as the Prime Minister of New Zealand, based on an analysis of postings retrieved from the most popular Chinese community question-answering (CQA) site—Zhihu. Drawing on critical discourse analysis (CDA), with the assistance of content analysis (CA), we reveal that Zhihu users’ assessments of Ardern’s electoral success are of a gendered divide in which women and men largely constitute the opposing opinion camps. In particular, male Internet users chiefly direct the discussion, attempting to rationalise the unsuitability of female politicians in Western-style democratic elections. In this process, they also legitimise the return of patriarchal orders to China, reflecting a domestic orientation of their engagement with international politics. The research findings shed light on the gender-politics nexus established in Chinese-language social media discourses.

Feature-based question routing in community question answering platforms

Community question answering (CQA) platforms are receiving increased attention and are becoming an indispensable source of information in different domains ranging from board games to physics. The success of these platforms dependent on how efficiently new questions are assigned to community experts, known ascalled question routing. In this paper, we address the problem of question routing by adopting a learning to rank approach over five CQA websites in the context of which we introduce 74 features and systematically classify them into content-based and social-based categories. Our extensive experiments on datasets from five real online question answering websites indicate that content-based features related to tags and topics as well as social features that are related to user characteristics and user temporality are effective for question routing. Our work shows the ability to improve performance compared to the state-of-the-art neural matchmaking methods that lack the interpretability offered by our work. The improvement can be as high as on average 2.47% and 1.10% in terms of common ranking metrics, Normalized Discounted Cumulative Gain (NDCG) and Mean Average Precision (MAP) respectively, compared to our best baselines.

Combining Latent Factor Model for Dynamic Recommendations in Community Question Answering Forums.

Community Question Answering (CQA) web service provides a platform for people to share knowledge. Quora, Stack Overflow, and Yahoo! Answers are few sites where questioners post their queries and answerers respond to their respective queries. Due to the ease of use and quick responsiveness of the CQA platform, these sites are being widely adopted by the community. For better usability, there is a dire need to route the question toward the relevant answerers. To fulfil this gap, recommender systems play an important role in identifying the relevant answerers. To map the user interests more effectively, this research work proposed a dynamic feature representation of the latent user attributes for user profiling. The latent features are mapped by leveraging the Latent Dirichlet Allocation (LDA) for topic modelling of user data. The proposed recommendation model segments the user profile based on these latent user profiles incorporating the incremental learning of the users' interests to produce the relevant recommendations in near real time. The experimental setup generated recommendation lists of variable sizes and evaluated using multiple evaluation metrics, such as mean average precision, recall, throughput, and different quality metrics, such as discounted cumulative gain and mean reciprocal rank. The results showed that the proposed model provided a better quality of recommendations in CQA forums, which is promising for future research in this domain.

Knowledge-enhanced attentive learning for answer selection in community question answering systems

In a community question-answering (CQA) system, the answer selection task is used to identify the best answer for a specific question. This plays a key role in improving service quality by recommending appropriate answers to new questions. Recent advances in CQA answer selection have focused on enhancing performance by incorporating community information, and particularly the expertise (previous answers) and authority (position in the social network) of a respondent. However, existing approaches to incorporating this information are limited, as they (a) consider either the expertise or the authority, but not both; (b) ignore domain knowledge that could differentiate between the topics of previous answers; or (c) simply use authority information to adjust the similarity score, rather than fully integrating it into the process of measuring the similarity between the question and answer segments. We propose a new approach called the knowledge-enhanced attentive answer selection (KAAS) model, which enhances performance by (a) considering both the expertise and the authority of the answerer; (b) utilizing human-labeled tags, a taxonomy of tags, and votes as domain knowledge to infer the expertise of the respondent; (c) using a matrix decomposition of the social network (based on ‘following’ relationships) to infer the authority of the respondent and incorporating this information into the process of evaluating the similarity between segments. In addition, we incorporate an external knowledge graph to capture more professional information for CQA systems for vertical communities. We also adopt an attention mechanism to integrate our analysis of both questions and answers texts and the aforementioned community information. Experiments with both vertical and general CQA sites demonstrate the superior performance of the proposed KAAS model.

A Collaborative AI-Enabled Pretrained Language Model for AIoT Domain Question Answering

Large-scale knowledge in the Artificial Intelligence of Things (AIoT) field urgently needs effective models to understand human language and automatically answer questions. Pre-trained language models (PLMs) achieve state-of-the-art performance on some question answering (QA) datasets, but few models can answer questions on AIoT domain knowledge. Currently, AIoT domain lacks sufficient QA datasets and large-scale pre-training corpora. We propose RoBERTa-AIoT to address the problem of the lack of high-quality large-scale labeled AIoT QA datasets. We construct an AIoT corpus to further pre-train RoBERTa and BERT. RoBERTa-AIoT and BERT-AIoT leverage unsupervised pre-training on a large corpus composed of AIoT-oriented Wikipedia webpages to learn more domain-specific context and improve performance on the AIoT QA tasks. To fine-tune and evaluate the model, we construct 3 AIoT QA datasets based on the community QA websites. We evaluate our approach on these datasets and the experimental results demonstrate the significant improvements of our approach.

Remediating textbook deficiencies by leveraging community question answers.

The paper presents a method for recommending augmentations against conceptual gaps in textbooks. Question Answer (QA) pairs from community question-answering (cQA) forums are noted to offer precise and comprehensive illustrations of concepts. Our proposed method retrieves QA pairs for a target concept to suggest two types of augmentations: basic and supplementary. Basic augmentations are suggested for the concepts on which a textbook lacks fundamental references. We identified such deficiencies by employing a supervised machine learning-based approach trained on 12 features concerning the textbook’s discourse. Supplementary augmentations aiming for additional references are suggested for all the concepts. Retrieved QA pairs were filtered to ensure their comprehensiveness for the target students. The proposed augmentation system was deployed using a web-based interface. We collected 28 Indian textbooks and manually curated them to create gold standards for assessing our proposed system. Analyzing expert opinions and adopting an equivalent pretest-posttest setup for the students, the quality of these augmentations was quantified. We evaluated the usability of the interface from students’ responses. Both system and human-based evaluations indicated that the suggested augmentations addressed the concept-specific deficiency and provided additional materials to stimulate learning interest. The learning interface was easy-to-use and showcased these augmentations effectively.

Answer selection in community question answering exploiting knowledge graph and context information

With the increasing popularity of knowledge graph (KG), many applications such as sentiment analysis, trend prediction, and question answering use KG for better performance. Despite the obvious usefulness of commonsense and factual information in the KGs, to the best of our knowledge, KGs have been rarely integrated into the task of answer selection in community question answering (CQA). In this paper, we propose a novel answer selection method in CQA by using the knowledge embedded in KGs. We also learn a latent-variable model for learning the representations of the question and answer, jointly optimizing generative and discriminative objectives. It also uses the question category for producing context-aware representations for questions and answers. Moreover, the model uses variational autoencoders (VAE) in a multi-task learning process with a classifier to produce class-specific representations for answers. The experimental results on three widely used datasets demonstrate that our proposed method is effective and outperforms the existing baselines significantly.

Improving Medical Q&A Matching by Augmenting Dual-Channel Attention with Global Similarity.

The emergence of online medical question-answer communities has helped to balance the supply of medical resources. However, the dramatic increase in the number of patients consulting online resources has resulted in a large number of repetitive medical questions, significantly reducing the efficiency of doctors in answering these questions. To improve the efficiency of online consultations, a large number of deep learning methods have been used for medical question-answer matching tasks. Medical question-answer matching involves identifying the best answer to a given question from a set of candidate answers. Previous studies have focused on representation-based and interaction-based question-answer pairs, with little attention paid to the effect of noise words on matching. Moreover, only local-level information was used for similarity modeling, ignoring the importance of global-level information. In this paper, we propose a dual-channel attention with global similarity (DCAG) framework to address the above issues in question-answer matching. The introduction of a self-attention mechanism assigns a different weight to each word in questions and answers, reducing the noise of “useless words” in sentences. After the text representations were obtained through the dual-channel attention model, a gating mechanism was introduced for global similarity modeling. The experimental results on the cMedQA v1.0 dataset show that our framework significantly outperformed existing state-of-the-art models, especially those using pretrained BERT models for word embedding, improving the top-1 accuracy to 75.6%.

CQAs: Community Question Answering System Using Ensemble Learning Techniques for Job Assistantship

CQAs: Community Question Answering System Using Ensemble Learning Techniques for Job Assistantship

High-quality domain expert finding method in CQA based on multi-granularity semantic analysis and interest drift

Expert finding is an important research field in community question answering (CQA). Traditional expert finding methods mainly exploit topic analysis and authority calculation methods to identify high-quality experts in certain fields. To avoid recommending questions to those experts who do not display the willingness or ability to provide high-quality answers, user interest drift and user quality should be considered. This study proposes a novel method named high-quality domain expert finding in CQA based on multi-granularity semantic analysis and interest drift (HQExpert). Firstly, HQExpert considers different semantic granularities by employing two models, a coarse-grained topic model LC-LDA and a fine-grained model (BERT), to capture the domain information of questions and users more accurately. Secondly, to address the diverse interests of the users, a user interest drift model in HQExpert is developed to dynamically represent the changes in the interests of the users at different periods. In addition, a user quality model is developed to further optimize the professional level of the user, finding experts who can provide high-quality answers and are interested in the current question. Finally, extensive experiments on two datasets from different domains demonstrate that the proposed HQExpert model can significantly improve the accuracy of finding high-quality experts.

Research on Knowledge Exchange Efficiency Measurement of Technical Question-Answering Community Based on SBM-Malmquist

Research on Knowledge Exchange Efficiency Measurement of Technical Question-Answering Community Based on SBM-Malmquist

Multi-hop interactive attention based classification network for expert recommendation

Community question answering (CQA) is a popular platform where users can ask questions or solve the questions proposed by other users. The expert recommendation aims at providing high-quality answers for the newly proposed questions in time, which is the key to a successful CQA. Questions in CQA usually consist of two parts, a subject which describes the main point, and a body which gives the details of the question. In previous studies, researchers usually ignore the differences between the subject and the body and concatenate them as a whole. In this paper, we propose a multi-hop interactive attention based classification network (MIACN) to recommend experts for newly proposed questions. In our model, the subject and the body are seen as two separate parts. A multi-hop attention is used to capture the multiple latent interactions among the two parts. Then, a high-level representation of the question is generated from the interactions. Experiment results on two real-world datasets demonstrate the effectiveness of our model.

Why Answer this Question? Experts’ Behaviors on Educational Community Question-Answering Platforms

This study explores the factors that influence experts’ regular contribution to educational community question-answering (CQA) platforms. Providing answers is essential for sharing knowledge on CQA platforms, but it also affects learners’ progressive inquiry. Therefore, the purpose of this study is to develop and test a theoretical model that aims to explain which factors influence whether experts answer questions on educational CQA platforms and how these factors correlate with each other to form a “map” of experts’ respective behavior. We examined experts’ perceptions of three dimensions: the CQA platform’s usability, the quality of questions asked, and the added value of answering these questions. We examined the factors involved in these dimensions from the perspective of the Theory of Planned Behavior to connect them with the experts’ perceptions, intentions, and actions on a CQA platform. As our case study, we took the 100mentors web and mobile app, a small-scale platform that addresses learning communities around the world, and we conducted a survey for their registered experts (N=126). The factorial structure indicated that experts first perceived the question quality mostly based on its relevance to their expertise or experience (question quality); secondly, that their intention to answer was mainly set by their motives to make a difference for the learner and partially by the user-friendliness of the platform (added value of answering and CQA platform’s usability); and finally, that their actions were connected to the regular use of the platform for answer-sharing (CQA platform’s usability). A future research challenge is to test the factorial structure in large-scale educational CQA platforms. The further confirmation of the expert behavior pattern can have a practical implication for the platforms to guide their expert community more efficiently and for the learners to pursue their learning through progressive inquiry.

CQA Transformer Models in the Home Improvement Domain

To find answers for subjective questions about many topics through Q\&A forums, questioners and answerers can cooperatively help themselves by sharing their doubts or answers based on their background and life experiences. These experiences can help machines redirect questioners to find better answers based on community question-answering models. This work proposes a comparative analysis of the pairwise community answer retrieval models in the home improvement domain considering different kinds of user question context information. Community Question-Answering (CQA) models must rank candidate answers in decreasing order of relevance for a user question. Our contribution consists of transformer-based language models using different kinds of user information to accurate the model generalisation. To train our model, we propose a proper CQA dataset in the home improvement domain that consists of information extracted from community forums, including question context information. We evaluate our approach by comparing the performance of each baseline model based on rank-aware evaluation measures.

Learning English and Arabic question similarity with Siamese Neural Networks in community question answering services

In this paper, we tackle the task of similar question retrieval (QR) which is essential for Community Question Answering (cQA) and aims to retrieve historical questions that are semantically equivalent to the new queries. Over time, with the sharp increase of community archives and the accumulation of duplicated questions, the QR problem has become increasingly challenging due to the shortness of the community questions as well as the word mismatch problem as users can formulate the same query using different wording. Although many efforts have been devoted to address this problem, existing methods mostly relied on supervised models which significantly depend on massive training data sets and manual feature engineering. Such methods are chiefly constrained by their specificities that ignore the word order and do not capture enough syntactic and semantic information in questions. In this paper, we rely on Neural Networks (NNs) which use a deep analysis of words and questions to take into consideration the semantics as well as the structure of questions to predict the semantic text similarity. We propose a deep learning approach based on a Siamese architecture with Long Short-Term Memory (LSTM) networks, augmented with an attention mechanism to let the model give different words different attention while modeling questions. We also explore the use of Convolutional Neural Networks (CNN) nested within the Siamese architecture to retrieve relevant questions. Different similarity measures were tested to predict the semantic similarity between the pairs of questions. To evaluate the proposed approach, we conducted experiments on large-scale datasets in English and Arabic.

Profiling Users for Question Answering Communities via Flow-Based Constrained Co-Embedding Model

In this article, we study the task of user profiling in question answering communities (QACs). Previous user profiling algorithms suffer from a number of defects: they regard users and words as atomic units, leading to the mismatch between them; they are designed for other applications but not for QACs; and some semantic profiling algorithms do not co-embed users and words, leading to making the affinity measurement between them difficult. To improve the profiling performance, we propose a neural Flow-based Constrained Co-embedding Model, abbreviated as FCCM. FCCM jointly co-embeds the vector representations of both users and words in QACs such that the affinities between them can be semantically measured. Specifically, FCCM extends the standard variational auto-encoder model to enforce the inferred embeddings of users and words subject to the voting constraint, i.e., given a question and the users who answer this question in the community, representations of the users whose answers receive more votes are closer to the representations of the words associated with these answers, compared with representations of whose receiving fewer votes. In addition, FCCM integrates normalizing flow into the variational auto-encoder framework to avoid the assumption that the distributions of the embeddings are Gaussian, making the inferred embeddings fit the real distributions of the data better. Experimental results on a Chinese Zhihu question answering dataset demonstrate the effectiveness of our proposed FCCM model for the task of user profiling in QACs.

AskMe: joint individual-level and community-level behavior interaction for question recommendation

Questions in Community Question Answering (CQA) sites are recommended to users, mainly based on users' interest extracted from questions that users have answered or have asked. However, there is a general phenomenon that users answer fewer questions while pay more attention to follow questions and vote answers. This can impact the performance when recommending questions to users (for obtaining their answers) by using their historical answering behaviors on existing studies. To address the data sparsity issue, we propose AskMe, which aims to leverage the rich, hybrid behavior interactions in CQA to improve the question recommendation performance. On the one hand, we model the rich correlations between the users' diverse behaviors (e.g., answer, follow, vote) to obtain the individual-level behavior interaction. On the other hand, we model the sophisticated behavioral associations between similar users to obtain the community-level behavior interaction. Finally, we propose the way of element-level fusion to mix these two kinds of interactions together to predict the ranking scores. A dataset collected from Zhihu (1126 users, 219434 questions) is utilized to evaluate the performance of the proposed model, and the experimental results show that our model has gained the best performance compared to baseline methods, especially when the historical answering behaviors data is scarce.