Community Question Answering Research Articles

Evaluating Answer Qualities on Q&A Community Sites (StackOverFlow)

Social Networking sites have gained much popularity in the recent years due to the widespread use of internet and availability of huge amounts of information. One kind of social network is Question Answering Community sites like StackOverflow, Quora and many more. These sites facilitate the user to ask their query on such sites using natural language and get the answers to their queries in natural language. There are many challenges to face when achieving above goals. One of the goals is to find the valid answers out of available answers and present it to the user, so as to save the user from going through multiple answers for a particular question and selecting the valid or appropriate answer. In this paper, we propose a system that finds the best answer from all the available answers based on answer content and the relationship between question and answer. We trained the system using three different classifiers and noted the accuracy results of each; the classifier which gave maximum accuracy was selected.

Multi-modal multi-view Bayesian semantic embedding for community question answering

Semantic embedding has demonstrated its value in latent representation learning of data, and can be effectively adopted for many applications. However, it is difficult to propose a joint learning framework for semantic embedding in Community Question Answer (CQA), because CQA data have multi-view and sparse properties. In this paper, we propose a generic Multi-modal Multi-view Semantic Embedding (MMSE) framework via a Bayesian model for question answering. Compared with existing semantic learning methods, the proposed model mainly has two advantages: (1) To deal with the multi-view property, we utilize the Gaussian topic model to learn semantic embedding from both local view and global view. (2) To deal with the sparse property of question answer pairs in CQA, social structure information is incorporated to enhance the quality of general text content semantic embedding from other answers by using the shared topic distribution to model the relationship between these two modalities (user relationship and text content). We evaluate our model for question answering and expert finding task, and the experimental results on two real-world datasets show the effectiveness of our MMSE model for semantic embedding learning.

Arabic community question answering

AbstractWe analyze resources and models for Arabic community Question Answering (cQA). In particular, we focus on CQA-MD, our cQA corpus for Arabic in the domain of medical forums. We describe the corpus and the main challenges it poses due to its mix of informal and formal language, and of different Arabic dialects, as well as due to its medical nature. We further present a shared task on cQA at SemEval, the International Workshop on Semantic Evaluation, based on this corpus. We discuss the features and the machine learning approaches used by the teams who participated in the task, with focus on the models that exploit syntactic information using convolutional tree kernels and neural word embeddings. We further analyze and extend the outcome of the SemEval challenge by training a meta-classifier combining the output of several systems. This allows us to compare different features and different learning algorithms in an indirect way. Finally, we analyze the most frequent errors common to all approaches, categorizing them into prototypical cases, and zooming into the way syntactic information in tree kernel approaches can help solve some of the most difficult cases. We believe that our analysis and the lessons learned from the process of corpus creation as well as from the shared task analysis will be helpful for future research on Arabic cQA.

Software expert discovery via knowledge domain embeddings in a collaborative network

Community Question Answering (CQA) websites can be claimed as the most major venues for knowledge sharing, and the most effective way of exchanging knowledge at present. Considering that massive amount of users are participating online and generating huge amount data, management of knowledge here systematically can be challenging. Expert recommendation is one of the major challenges, as it highlights users in CQA with potential expertise, which may help match unresolved questions with existing high quality answers while at the same time may help external services like human resource systems as another reference to evaluate their candidates. In this paper, we in this work we propose to exploring experts in CQA websites. We take advantage of recent distributed word representation technology to help summarize text chunks, and in a semantic view exploiting the relationships between natural language phrases to extract latent knowledge domains. By domains, the users’ expertise is determined on their historical performance, and a rank can be compute to given recommendation accordingly. In particular, Stack Overflow is chosen as our dataset to test and evaluate our work, where inclusive experiment shows our competence.

A user ranking algorithm for efficient information management of community sites using spectral clustering and folksonomy

Community question answering (CQA) sites are the major platform for information sharing where posts are created by users as questions and answers. A large number of posts are created on a day-to-day basis, which raise the problem of information management of these sites. Multiple techniques are suggested in existing research for efficient management of CQA sites. Many of the existing techniques used the user ranking for managing the CQA sites but ignored the tagging data and user subject area. In this article, a user ranking method is derived using spectral clustering for posts management by considering the tagging data of CQA sites. Folksonomy is used to build relationship between tags, posts and users. The proposed method is developed in three stages. In first stage, the folksonomy relation is created and user similarity graph is built with the help of tag frequency-inverse post frequency and text similarity techniques. In the second stage, spectral clustering algorithm is applied on user similarity graph to group the similar users. Finally, in third stage, rank of users is identified from the clusters based on user’s information. The clustered users and rank of the users are generated as the output of the proposed algorithm that can provide a way of efficient information management. The experimental results show that the proposed user ranking algorithm outperforms the other considered ranking algorithms and can be helpful for information management of CQA sites. Some real-life applications of information management in CQA sites using the proposed work are also demonstrated in this article.

Joint modeling of users, questions and answers for answer selection in CQA

In this paper, we propose solutions to advance answer selection in Community Question Answering (CQA). Automatically selecting correct answers can significantly improve intelligence for CQA, as users are not required to browse the large quantity of texts and select the right answers manually. Also, automatic answers selection can minimize the time for satisfying users seeking the correct answers and maximize user engagement with the site. Unlike previous works, we propose a hybrid attention mechanism to model question-answer pairs. Specifically, for each word, we calculate the intra-sentence attention indicating its local importance and the inter-sentence attention implying its importance to the counterpart sentence. The inter-sentence attention is based on the interactions between question-answer pairs, and the combination of these two attention mechanisms enables us to align the most informative parts in question-answer pairs for sentence matching. Additionally, we exploit user information for answer selection due to the fact that users are more likely to provide correct answers in their areas of expertise. We model users from their written answers to alleviate data sparsity problem, and then learn user representations according to the informative parts in sentences that are useful for question-answer matching task. This mean of modelling users can bridge the semantic gap between different users, as similar users may have the same way of wording their answers. The representations of users, questions and answers are learnt in an end-to-end neural network in a mean that best explains the interrelation between question-answer pairs. We validate the proposed model on a public dataset, and demonstrate its advantages over the baselines with thorough experiments.

Integrating heterogeneous sources for predicting question temporal anchors across Yahoo! Answers

Modern Community Question Answering (CQA) web forums provide the possibility to browse their archives using question-like search queries as in Information Retrieval (IR) systems. Although these traditional IR methods have become very successful at fetching semantically related questions, they typically leave unconsidered their temporal relations. That is to say, a group of questions may be asked more often during specific recurring time lines despite being semantically unrelated. In fact, predicting temporal aspects would not only assist these platforms in widening the semantic diversity of their search results, but also in re-stating questions that need to refresh their answers and in producing more dynamic, especially temporally-anchored, displays.In this paper, we devised a new set of time-frame specific categories for CQA questions, which is obtained by fusing two distinct earlier taxonomies (i.e., [29] and [50]). These new categories are then utilized in a large crowd-sourcing based human annotation effort. Accordingly, we present a systematical analysis of its results in terms of complexity and degree of difficulty as it relates to the different question topics11The new annotated corpus will be made publicly available upon acceptance under https://doi.org/10.13140/RG.2.2.23360.38407.Incidentally, through a large number of experiments, we investigate the effectiveness of a wider variety of linguistic features compared to what has been done in previous works. We additionally mix evidence/features distilled directly and indirectly from questions by capitalizing on their related web search results. We finally investigate the impact and effectiveness of multi-view learning to boost a large variety of multi-class supervised learners by optimizing a latent layer build on top of two views: one composed of features harvested from questions, and the other from CQA meta data and evidence extracted from web resources (i.e., snippets and Internet archives).

The Big Five: Discovering Linguistic Characteristics that Typify Distinct Personality Traits across Yahoo! Answers Members

In psychology, it is widely believed that there are five big factors that determine the different personality traits: Extraversion, Agreeableness, Conscientiousness and Neuroticism as well as Openness. In the last years, researchers have started to examine how these factors are manifested across several social networks like Facebook and Twitter. However, to the best of our knowledge, other kinds of social networks such as social/informational question-answering communities (e.g., Yahoo! Answers) have been left unexplored. Therefore, this work explores several predictive models to automatically recognize these factors across Yahoo! Answers members. As a means of devising powerful generalizations, these models were combined with assorted linguistic features. Since we do not have access to ask community members to volunteer for taking the personality test, we built a study corpus by conducting a discourse analysis based on deconstructing the test into 112 adjectives. Our results reveal that it is plausible to lessen the dependency upon answered tests and that effective models across distinct factors are sharply different. Also, sentiment analysis and dependency parsing proven to be fundamental to deal with extraversion, agreeableness and conscientiousness. Furthermore, medium and low levels of neuroticism were found to be related to initial stages of depression and anxiety disorders.

Exploiting cross-source knowledge for warming up community question answering services

Community Question Answering (CQA) services such as Yahoo! Answers, Quora and StackOverflow are collaborative platforms where users can share and exchange their knowledge explicitly by asking and answering questions. One essential task in CQA is learning topical expertise of users, which may benefit many applications such as question routing and best answers identification. One limitation of existing related works is that they only consider the warm-start users who have posted many questions or answers, while ignoring cold-start users who have few posts. In this paper, we aim to exploit knowledge from cross sources such as GitHub and StackOverflow to build up the richer views of expertise for better CQA. Inspired by the idea of Bayesian co-training, we propose a topical expertise model from the perspective of multi-view learning. Specifically, we incorporate the consistency existing among multiple views into a unified probabilistic graphic model. Comprehensive experiments on two real-world datasets demonstrate the performance of our proposed model with the comparison of some state-of-the-art ones.

Retrieving people: Identifying potential answerers in Community Question‐Answering

Community Question‐Answering (CQA) sites have become popular venues where people can ask questions, seek information, or share knowledge with a user community. Although responses on CQA sites are obviously slower than information retrieved by a search engine, one of the most frustrating aspects of CQAs occurs when an asker's posted question does not receive a reasonable answer or remains unanswered. CQA sites could improve users' experience by identifying potential answerers and routing appropriate questions to them. In this paper, we predict the potential answerers based on question content and user profiles. Our approach builds user profiles based on past activity. When a new question is posted, the proposed method computes scores between the question and all user profiles to find the potential answerers. We conduct extensive experimental evaluations on two popular CQA sites ‐ Yahoo! Answers and Stack Overflow ‐ to show the effectiveness of our algorithm. The results show that our technique is able to predict a small group of 1000 users from which at least one user will answer the question with a probability higher than 50% in both CQA sites. Further analysis indicates that topic interest and activity level can improve the correctness of our approach.

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.

ColdRoute: effective routing of cold questions in stack exchange sites

Routing questions in Community Question Answer services (CQAs) such as Stack Exchange sites is a well-studied problem. Yet, cold-start -- a phenomena observed when a new question is posted is not well addressed by existing approaches. Additionally, cold questions posted by new askers present significant challenges to state-of-the-art approaches. We propose ColdRoute to address these challenges. ColdRoute is able to handle the task of routing cold questions posted by new or existing askers to matching experts. Specifically, we use Factorization Machines on the one-hot encoding of critical features such as question tags and compare our approach to well-studied techniques such as CQARank and semantic matching (LDA, BoW, and Doc2Vec). Using data from eight stack exchange sites, we are able to improve upon the routing metrics (Precision$@1$, Accuracy, MRR) over the state-of-the-art models such as semantic matching by $159.5\%$,$31.84\%$, and $40.36\%$ for cold questions posted by existing askers, and $123.1\%$, $27.03\%$, and $34.81\%$ for cold questions posted by new askers respectively.

Expert Finding in Community Question-Answering for Post Recommendation

Community question answering system is a perfect example of platform where people participate to seek expertise on their topic of interest. But information overload, finding the expertise level of users and trustworthy answers remain key challenges within these communities. Moreover, people do not look for personal advices but expert views on such platforms therefore; expert finding is an integral part of these communities. In order to trust someone's opinion who is not known in person by the users of the community, it is necessary to find the credibility of such person. By determining expertise levels of users, authenticity of their posts can easily be determined. Also, by identifying experts, each expert will be shown relevant posts to indulge in so that he can use his knowledge and skills to give valid and correct answers. For users too, it will be easy to find reliable answers, once they get to know the expertise level of the answerers. Motivated by these facts, we put forward a framework for finding experts in online question answer community (stackoverflow) referred to as Expert Recommender System which uses a well-recognized global-trust metric, PageRankTM for finding experts in the community building a Trust-based system and then uses collaborative filtering to find similar experts based on their level of expertise and their topics of interests to a particular user. Once we have the top- k similar experts to a given expert, that expert is recommended with posts to collaborate upon, based on activities done by his top-k neighbor experts. The framework is evaluated for its performance and it clearly indicates the effectiveness of the system.

Detecting Misflagged Duplicate Questions in Community Question-Answering Archives

In this paper we introduce the task of misflagged duplicate question detection for question pairs in community question-answer (cQA) archives and compare it to the more standard task of detecting valid duplicate questions. A misflagged duplicate is a question that has been erroneously hand-flagged by the community as a duplicate of an archived one, where the two questions are not actually the same. We find that form is flagged duplicate detection, meta data features that capture user authority, question quality, and relational data between questions, outperform pure text-based methods, while for regular duplicate detection a combination of meta data features and semantic features gives the best results. We show that misflagged duplicate questions are even more challenging to model than regular duplicate question detection, but that good results can still be obtained.

QDEE: Question Difficulty and Expertise Estimation in Community Question Answering Sites

In this paper, we present a framework for Question Difficulty and Expertise Estimation (QDEE) in Community Question Answering sites (CQAs) such as Yahoo! Answers and Stack Overflow, which tackles a fundamental challenge in crowdsourcing: how to appropriately route and assign questions to users with the suitable expertise. This problem domain has been the subject of much research and includes both language-agnostic as well as language conscious solutions. We bring to bear a key language-agnostic insight: that users gain expertise and therefore tend to ask as well as answer more difficult questions over time. We use this insight within the popular competition (directed) graph model to estimate question difficulty and user expertise by identifying key hierarchical structure within said model. An important and novel contribution here is the application of ``social agony'' to this problem domain. Difficulty levels of newly posted questions (the cold-start problem) are estimated by using our QDEE framework and additional textual features. We also propose a model to route newly posted questions to appropriate users based on the difficulty level of the question and the expertise of the user. Extensive experiments on real world CQAs such as Yahoo! Answers and Stack Overflow data demonstrate the improved efficacy of our approach over contemporary state-of-the-art models.

Factoid Question Answering with Distant Supervision.

Automatic question answering (QA), which can greatly facilitate the access to information, is an important task in artificial intelligence. Recent years have witnessed the development of QA methods based on deep learning. However, a great amount of data is needed to train deep neural networks, and it is laborious to annotate training data for factoid QA of new domains or languages. In this paper, a distantly supervised method is proposed to automatically generate QA pairs. Additional efforts are paid to let the generated questions reflect the query interests and expression styles of users by exploring the community QA. Specifically, the generated questions are selected according to the estimated probabilities they are asked. Diverse paraphrases of questions are mined from community QA data, considering that the model trained on monotonous synthetic questions is very sensitive to variants of question expressions. Experimental results show that the model solely trained on generated data via the distant supervision and mined paraphrases could answer real-world questions with the accuracy of 49.34%. When limited annotated training data is available, significant improvements could be achieved by incorporating the generated data. An improvement of 1.35 absolute points is still observed on WebQA, a dataset with large-scale annotated training samples.

Not all the questions are (equally) difficult. An hybrid approach to CQA in Arabic

In the past we faced the problem of Community Question Answering using an unified approach. Some of the questions, however, are easier to be approached by a conventional rule-based system. In this paper we explore this direction.

Identifying reputation collectors in community question answering (CQA) sites: Exploring the dark side of social media

This research aims to identify users who are posting as well as encouraging others to post low quality and duplicate contents on community question answering sites. The good guys called Caretakers and the bad guys called Reputation Collectors are characterised by their behaviour, answering pattern and reputation points. The proposed system is developed and analysed over publicly available Stack Exchange data dump. A graph-based methodology is employed to derive the characteristic of Reputation Collectors and Caretakers. Results reveal that Reputation Collectors are primary sources of low-quality answers as well as answers to duplicate questions posted on the site. The Caretakers answer limited questions of challenging nature and fetches maximum reputation against those questions whereas Reputation Collectors answers have so many low quality and duplicate questions to gain the reputation point. We have developed algorithms to identify the Caretakers and Reputation Collectors of the site. Our analysis finds that 1.05% of Reputation Collectors post 18.88% of low-quality answers. This study extends previous research by identifying the Reputation Collectors and how they collect their reputation points.

Identity and performance in technical Q&A

ABSTRACTIdentity and the different roles identities play in social question-answering communities have long been discussed from both a theoretical and empirical standpoint. Identity is usually analysed in ways that emphasise a transaction, and many studies use third-party raters to assign value judgements to these factors, which may not be relevant to a community. In this article, we examine identity in Stack Overflow, a question and answer site dedicated to solving computer-programming problems, which has a competitive community run reputation system. Profiles on Stack Overflow are highly customizable, allowing users to choose the level of personal information they want to share: from extensive to none. We develop a categorisation scheme using grounded theory to develop definitions of identity, and analyse behaviour based on these definitions. We find that the choice of identity is diverse within the community and that there is a correlation with identifiers and increased reputation earning among the general population. An analysis of elite users, however, indicates that identity is closely tied to membership length, but not to performance. The results indicate that allowing identity choices does affect system efficacy or user outcomes.

Survey Paper on a Pairwise Learning to Rank Model for Answer Selection in Community Question Answer (CQA) System

Survey Paper on a Pairwise Learning to Rank Model for Answer Selection in Community Question Answer (CQA) System