Community-based Question Answering Research Articles

PlanHelper

Community-based Question Answering (CQA) platforms can provide rich experience and suggestions for people who seek to construct Activity Plans (AP), such as bodybuilding or sightseeing. However, answer posts in CQA platforms could be too unstructured and overwhelming to be easily applied to AP construction, as validated by our formative study for understanding relevant user challenges. We therefore proposed an answer-post processing pipeline, based on which we built PlanHelper, a tool assisting users in processing the CQA information and constructing AP interactively. We conducted a within-subject study (N=24) with a Quora-like interface as the baseline. Results suggested that when creating AP with PlanHelper, users were significantly more satisfied with the informational support and more engaged during the interaction. Moreover, we performed an in-depth analysis on the user behaviors with PlanHelper and summarized the design considerations for such supporting tools.

Question routing via activity-weighted modularity-enhanced factorization

Question Routing (QR) in Community-based Question Answering (CQA) websites aims at recommending newly posted questions to potential users who are most likely to provide “accepted answers”. Most of the existing approaches predict users’ expertise based on their past question answering behavior and the content of new questions. However, these approaches suffer from challenges in three aspects: (1) sparsity of users’ past records results in lack of personalized recommendation that at times does not match users’ interest or domain expertise, (2) modeling based on all questions and answers content makes periodic updates computationally expensive, and (3) while CQA sites are highly dynamic, they are mostly considered as static. This paper proposes a novel approach to QR that addresses the above challenges. It is based on dynamic modeling of users’ activity on topic communities. Experimental results on three real-world datasets demonstrate that the proposed model significantly outperforms competitive baseline models.

Xiao-Shih: A Self-Enriched Question Answering Bot With Machine Learning on Chinese-Based MOOCs

This article introduces Xiao-Shih, the first intelligent question answering bot on Chinese-based massive open online courses (MOOCs). Question answering is critical for solving individual problems. However, instructors on MOOCs must respond to many questions, and learners must wait a long time for answers. To address this issue, Xiao-Shih integrates many novel natural language processing and machine learning approaches to achieve state-of-the-art performance. Furthermore, Xiao-Shih has a built-in self-enriched mechanism for expanding the knowledge base through open community-based question answering. This article proposes a novel approach, known as spreading question similarity (SQS), which iterates similar keywords on our keyword networks to find duplicate questions. Compared with BERT, an advanced neural language model, the results showed that SQS outperforms BERT on recall and accuracy above a prediction probability threshold of 0.8. After training, Xiao-Shih achieved a perfect correct rate. Furthermore, Xiao-Shih outperforms Jill Watson 1.0, which is a noted question answering bot, on answer rate with the self-enriched mechanism.

Booming Up the Long Tails: Discovering Potentially Contributive Users in Community-Based Question Answering Services

Community-based question answering (CQA) services such as Yahoo! Answers have been widely used by Internet users to get the answers for their inquiries. The CQA services totally rely on the contributions by the users. However, it is known that newcomers are prone to lose their interests and leave the communities. Thus, finding expert users in an early phase when they are still active is essential to improve the chances of motivating them to contribute to the communities further. In this paper, we propose a novel approach to discovering "potentially" contributive users from recently-joined users in CQA services. The likelihood of becoming a contributive user is defined by the user's expertise as well as availability, which we call the answer affordance. The main technical difficulty lies in the fact that such recently-joined users do not have abundant information accumulated for many years. We utilize a user's productive vocabulary to mitigate the lack of available information since the vocabulary is the most fundamental element that reveals his/her knowledge. Extensive experiments were conducted with a huge data set of Naver Knowledge-In (KiN), which is the dominating CQA service in Korea. We demonstrate that the top rankers selected by the answer affordance outperformed those by KiN in terms of the amount of answering activity.

Towards Predicting the Best Answers in Community-based Question-Answering Services

Community-based question-answering (CQA) services contribute to solving many difficult questions we have. For each question in such services, one best answer can be designated, among all answers, often by the asker. However, many questions on typical CQA sites are left without a best answer even if when good candidates are available. In this paper, we attempt to address the problem of predicting if an answer may be selected as the best answer, based on learning from labeled data. The key tasks include designing features measuring important aspects of an answer and identifying the most importance features. Experiments with a Stack Overflow dataset show that the contextual information among the answers should be the most important factor to consider.

Graph-Based Tri-Attention Network for Answer Ranking in CQA

In community-based question answering (CQA) platforms, automatic answer ranking for a given question is critical for finding potentially popular answers in early times. The mainstream approaches learn to generate answer ranking scores based on the matching degree between question and answer representations as well as the influence of respondents. However, they encounter two main limitations: (1) Correlations between answers in the same question are often overlooked. (2) Question and respondent representations are built independently of specific answers before affecting answer representations. To address the limitations, we devise a novel graph-based tri-attention network, namely GTAN, which has two innovations. First, GTAN proposes to construct a graph for each question and learn answer correlations from each graph through graph neural networks (GNNs). Second, based on the representations learned from GNNs, an alternating tri-attention method is developed to alternatively build target-aware respondent representations, answer-specific question representations, and context-aware answer representations by attention computation. GTAN finally integrates the above representations to generate answer ranking scores. Experiments on three real-world CQA datasets demonstrate GTAN significantly outperforms state-of-the-art answer ranking methods, validating the rationality of the network architecture.

Recency and quality-based ranking question in CQAs: A Stack Overflow case study

Recency ranking, in Community-based Question Answering (CQA), would refer to put recent answers in a list’s top positions. To be recent is not related to how new is the date of creation or editing of a given answer, but how current is the content of the answer. A good ranking should also consider the answers’ quality since a current but no quality answer may be useless. Similarly, a high-quality answer, presenting adequate text and references with obsolete information, may be valueless. Combining these two issues (recency and quality) is crucial as users usually hope for current solutions and need to have fast/easy access (top items in the ranking) to the best answers to solve their problems quickly. The CQAs usually provide voting mechanisms so that the users can indicate the best quality answers. However, this method is not concerned with the recency of the answers besides being a slow and subjective process, which does not keep up with new content’s dynamism. Therefore, we propose an automatic approach that, besides the quality, also considers the answer’s recency to generating the ranking. We have used textual and non-textual features that indicate the answers’ quality and recency, extracted from the users’ answers in the CQA environment as a whole. In our approach, quality is used to classify the answers between good and poor, using a threshold value, generating two sets of answers: high quality and low quality. Then, both sets are sorted into recency order. Finally, these sets are concatenated, giving rise to the final ranking, so that the best and most current answers are in the top positions. To verify our proposal’s effectiveness, we have performed a case study in Stack Overflow CQA with a set of experiments, using different combinations of characteristics and different learning to rank Stack Overflow. Then, our main contributions are: (1) an approach to ranking answers of a questions dataset on the recency and quality of an answer; (2) a thorough evaluation of 9 learning to rank algorithms, showing that Coordinate Ascent and LambdaMart have the best performance in this task; (3) a feature analysis, which has shown that features related to the age of the response contributed to improving the ranking performance taking recency and quality into account. Furthermore, as far as we know, it is the first work that considers the recency of an answer in this task.

Batch recommendation of experts to questions in community-based question-answering with a sailfish optimizer

To facilitate question-answering in community-based question-answering (CQA), this paper proposes an approach for the batch recommendation of answerers by optimizing the utilization of expert resources. First, questions and experts are modeled with a biterm topic model (BTM). Next, the answered questions are clustered based on a novel discrete sailfish optimizer (SFO) with a genetic algorithm (GA), and the topic distribution is obtained. Then, experts are ranked in each cluster based on activeness, recency, and professionalism. Considering the limited number of experts, to ensure that core questions are answered and to avoid repeated answers to similar or duplicate questions, coverage, answerability and the consumption of expert resources are taken as objects to be optimized. This scenario is formulated as a multiobjective optimization problem and is addressed by the proposed novel binary multiobjective SFO (MOSFO) with a GA. The solution of the model includes not only the selected questions to be answered but also the matching between the questions and experts. The proposed approach is evaluated with a real dataset, and the experimental results show that the proposed approach is feasible and has superior performance to the question-priority method, the expert-priority method and other swarm intelligence (SI) methods. This study is the first to make batch recommendations, providing a new idea and extending research on expert recommendation. Additionally, the approach can be used practically to improve the satisfaction of the knowledge needs of users by improving the answerability of high-coverage questions.

Harnessing Artificial Intelligence to Improve the Quality of Answers in Online Question-answering Health Forums

ABSTRACT Quality of answers in health-related community-based question answering (HCQA) forums has been a concern for both users and forum administrators. We conducted a two-phase study to better understand the quality of answers in HCQA forums. First, we employed machine learning to examine the quality of health content. We validated our algorithmic quality ratings by comparing them with those of two physicians. Second, using data from Yahoo! Answers Health section, we examined the effect of the quality of the first answer on the quality of the subsequent answers. Our results suggest that the quality of the subsequent answers is impacted by the quality of the first displayed answer. We further show that the impact of the first displayed answer is larger when the answerers are more familiar with the forum but smaller when the forum provides tips for answering questions. Our study helps HCQA forums to improve the overall quality of answers by 1- creating an algorithmic solution that reliably measures the quality of answers, and 2- adjusting the order of existing answers to encourage higher quality subsequent answers. Our findings also extend the applicability of the order effect to online forums and provide evidence that experienced users would be more influenced by the order effect in such forums.

Heterogeneous Community Question Answering via Social-Aware Multi-Modal Co-Attention Convolutional Matching

Nowadays, community-based question answering (CQA) systems are popular and have accumulated a large number of questions and answers provided by users. How to accurately match relevant answers for a given question is an essential function in CQA tasks. Recent effective methods utilize word-pair interactions between questions and answers for CQA matching. However, these approaches usually encode questions and answers independently and ignore the fact that they can complement and enhance each other to provide better representations and thus more implicit interactions can be captured. In addition, the visual information, social information and the variable-length problem are usually ignored by most existing approaches. In this paper, a Social-aware Multi-modal Co-attention Convolutional Matching method (SMCACM) is proposed, which models the multi-modal content and social context of questions and answers in a unified framework for CQA matching. A novel co-attention network is proposed to extract complementary information from questions and answers to enhance each other for obtaining better representations, through which our model can capture more implicit interactions between questions and answers. In addition to textual content, our model uses object detection techniques and a meta-path based heterogeneous social representation learning approach to take advantage of the visual content and social context in CQA systems, respectively. Finally, a pooling-based convolutional matching network is designed to infer the matching score based on the complemented questions and answers, which can accept variable-length answers as inputs without padding or cutting. Experimental results on two real-world datasets demonstrate the superior performance of SMCACM compared with other state-of-the-art algorithms.

Personalized Question Routing via Heterogeneous Network Embedding

Question Routing (QR) on Community-based Question Answering (CQA) websites aims at recommending answerers that have high probabilities of providing the “accepted answers” to new questions. The existing question routing algorithms simply predict the ranking of users based on query content. As a consequence, the question raiser information is ignored. On the other hand, they lack learnable scoring functions to explicitly compute ranking scores.To tackle these challenges, we propose NeRank that (1) jointly learns representations of question content, question raiser, and question answerers by a heterogeneous information network embedding algorithm and a long short-term memory (LSTM) model. The embeddings of the three types of entities are unified in the same latent space, and (2) conducts question routing for personalized queries, i.e., queries with two entities (question content, question raiser), by a convolutional scoring function taking the learned embeddings of all three types of entities as input. Using the scores, NeRank routes new questions to high-ranking answerers that are skillfulness in the question domain and have similar backgrounds to the question raiser.Experimental results show that NeRank significantly outperforms competitive baseline question routing models that ignore the raiser information in three ranking metrics. In addition, NeRank is convergeable in several thousand iterations and insensitive to parameter changes, which prove its effectiveness, scalability, and robustness.

Adversarial Training for Community Question Answer Selection Based on Multi-Scale Matching

Community-based question answering (CQA) websites represent an important source of information. As a result, the problem of matching the most valuable answers to their corresponding questions has become an increasingly popular research topic. We frame this task as a binary (relevant/irrelevant) classification problem, and present an adversarial training framework to alleviate label imbalance issue. We employ a generative model to iteratively sample a subset of challenging negative samples to fool our classification model. Both models are alternatively optimized using REINFORCE algorithm. The proposed method is completely different from previous ones, where negative samples in training set are directly used or uniformly down-sampled. Further, we propose using Multi-scale Matching which explicitly inspects the correlation between words and ngrams of different levels of granularity. We evaluate the proposed method on SemEval 2016 and SemEval 2017 datasets and achieves state-of-the-art or similar performance.

Pencarian Question-Answer Menggunakan Convolutional Neural Network Pada Topik Agama Berbahasa Indonesia

Community-based question answering (CQA) is formed to help people who search information that they need through a community. One condition that may occurs in CQA is when people cannot obtain the information that they need, thus they will post a new question. This condition can cause CQA archive increased because of duplicated questions. Therefore, it becomes important problems to find semantically similar questions from CQA archive towards a new question. In this study, we use convolutional neural network methods for semantic modeling of sentence to obtain words that they represent the content of documents and new question. The result for the process of finding the same question semantically to a new question (query) from the question-answer documents archive using the convolutional neural network method, obtained the mean average precision value is 0,422. Whereas by using vector space model, as a comparison, obtained mean average precision value is 0,282.
 Index Terms—community-based question answering, convolutional neural network, question retrieval

Multi-Label Community-Based Question Classification via Personalized Sequence Memory Network Learning

Multi-label community-based question classification is a challenging problem in Community-based Question Answering (CQA) services, arising in many real applications such as question navigation and expert finding. Most of the existing approaches consider the problem as content-based tag suggestion task, which suffers from the textual sparsity issue. Unlike the previous studies, we consider the problem of multi-label community-based question classification from the viewpoint of personalized sequence learning. We introduce the personalized sequence memory network that leverages not only the semantics of questions but also the personalized information of askers to provide the sequence tag learning function to capture the high-order tag dependency. The experiment on real-world dataset shows the effectiveness of our method.

Duplicate Detection in Programming Question Answering Communities

Community-based Question Answering (CQA) websites are attracting increasing numbers of users and contributors in recent years. However, duplicate questions frequently occur in CQA websites and are currently manually identified by the moderators. Automatic duplicate detection, on one hand, alleviates this laborious effort for moderators before taking close actions, and, on the other hand, helps question issuers quickly find answers. A number of studies have looked into related problems, but very limited works target Duplicate Detection in Programming CQA (PCQA), a branch of CQA that is dedicated to programmers. Existing works framed the task as a supervised learning problem on the question pairs and relied on only textual features. Moreover, the issue of selecting candidate duplicates from large volumes of historical questions is often un-addressed. To tackle these issues, we model duplicate detection as a two-stage “ranking-classification” problem over question pairs. In the first stage, we rank the historical questions according to their similarities to the newly issued question and select the top ranked ones as candidates to reduce the search space. In the second stage, we develop novel features that capture both textual similarity and latent semantics on question pairs, leveraging techniques in deep learning and information retrieval literature. Experiments on real-world questions about multiple programming languages demonstrate that our method works very well; in some cases, up to 25% improvement compared to the state-of-the-art benchmarks.

Question retrieval for community-based question answering via heterogeneous social influential network

Abstract Community-based question answering platforms have attracted substantial users to share knowledge and learn from each other. As the rapid enlargement of community-based question answering (CQA) platforms, quantities of overlapped questions emerge, which makes users confounded to select a proper reference. It is urgent for us to take effective automated algorithms to reuse historical questions with corresponding answers. In this paper, we focus on the problem with question retrieval, which aims to match historical questions that are relevant or semantically equivalent to resolve one’s query directly. The challenges in this task are the lexical gaps between questions for the word ambiguity and word mismatch problem. Furthermore, limited words in queried sentences cause sparsity of word features. To alleviate these challenges, we propose a novel framework named HSIN which encodes not only the question contents but also the asker’s social interactions to enhance the question embedding performance. More specifically, we apply random walk based learning method with recurrent neural network to match the similarities between asker’s question and historical questions proposed by other users. Extensive experiments on a large-scale dataset from a real world CQA site Quora show that employing the heterogeneous social network information outperforms the other state-of-the-art solutions in this task.

Unsupervised Latent Dirichlet Allocation for supervised question classification

Question answering systems assist users in satisfying their information needs more precisely by providing focused responses to their questions. Among the various systems developed for such a purpose, community-based question answering has recently received researchers’ attention due to the large amount of user-generated questions and answers in social question-and-answer platforms. Reusing such data sources requires an accurate information retrieval component enhanced by a question classifier. The question classification gives the system the possibility to have information about question categories to focus on questions and answers from relevant categories to the input question. In this paper, we propose a new method based on unsupervised Latent Dirichlet Allocation for classifying questions in community-based question answering. Our method first uses unsupervised topic modeling to extract topics from a large amount of unlabeled data. The learned topics are then used in the training phase to find their association with the available category labels in the training data. The category mixture of topics is finally used to predict the label of unseen data.

Temporal Interaction and Causal Influence in Community-Based Question Answering

During the last decade, community-based question answering (CQA) sites have accumulated a vast amount of questions and their crowdsourced answers over time. How to efficiently identify the quality of answers that are relevant to a given question has become an active line of research in CQA. The major challenge of CQA is the accurate selection of high-quality answers w.r.t given questions. Previous approaches tend to model the semantic matching between individual pair of one question and its corresponding answer (how fitting an answer is to a posted question). However, these works ignore the temporal interactions between answers (how previous answers influence the late posted answers). For example, a rational user likely adapts others’ opinions, revises his inclinations, and posts a more appropriate answer after understanding the given question and previously posted answers. As a result, this paper devises an architecture named Temporal Interaction and Causal Influence LSTM (TC-LSTM) to effectively leverage not only the causal influence between question-answer (how appropriate an answer is for a given question) but also the temporal interactions between answers-answer (how a high-quality answer gradually forms). In particular, long short-term memory (LSTM) is used to capture the explicit question-answer influence and the implicit answers-answer interactions. Experiments are conducted on SemEval 2015 CQA dataset for answer classification task and Baidu Zhidao Dataset for answer ranking task. The experimental results show the advantage of our model comparing with other state-of-the-art methods.

Query completion in community-based Question Answering search

Query completion has long been proved useful to help a user explore and express his information need. In general search, such completions can be generated from a large scale query log and other accessory information. However, without query log, how to generate query completion for community-based Question Answering (cQA) search remains a challenging problem. In this work, we propose a novel query completion algorithm based on ranking cQA questions with entity and phrase information for cQA search, and a demonstration system has been developed. Without involvement of query log, this method clearly helps users complete their queries. Empirical experiments on a large scale cQA dataset show that the proposed algorithm can successfully improve user experience.

Community-Based Question Answering via Contextual Ranking Metric Network Learning

The exponential growth of information on Community-based Question Answering (CQA) sites has raised the challenges for the accurate matching of high-quality answers to the given questions. Many existing approaches learn the matching model mainly based on the semantic similarity between questions and answers, which can not effectively handle the ambiguity problem of questions and the sparsity problem of CQA data. In this paper, we propose to solve these two problems by exploiting users' social contexts. Specifically, we propose a novel framework for CQA task by exploiting both the question-answer content in CQA site and users' social contexts. The experiment on real-world dataset shows the effectiveness of our method.