sensors-logo

Journal Browser

Journal Browser

Community Question Answering: From Recent Advances in Methods, Techniques, Models and Applications to Future Perspectives

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensor Networks".

Deadline for manuscript submissions: closed (30 November 2022) | Viewed by 4092

Special Issue Editors


E-Mail Website
Guest Editor
Institute of High Performance Computing and Networks (ICAR) of the National Research Council of Italy (CNR), 87036 Rende, Italy
Interests: data mining; machine learning; recommender systems; social network analysis; text mining; semi-structured data analysis
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Institute for High-Performance Computing and Networking (ICAR), National Research Council (CNR), 87036 Rende, Italy
Interests: machine intelligence; machine learning; knowledge discovery; (intelligent) information systems; knowledge-based systems; recommender systems; text analysis; community question answering; (social) network/media analysis; decision support; behavioral analysis; semistructured data analysis; data mining
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Community question answering (CQA) encompasses a broad class of services for knowledge sharing and collaborative learning that allow askers to post questions upon specific information needs, in an attempt to receive satisfactory responses from expert answerers of the consulted community. Essentially, in CQA, the information needs of askers together with the wisdom, reply willingness, and collective intelligence of answerers form altogether a human and social computation system. Within the latter, askers and answerers operate as human sensors. The former report the emergence of an information need in the community. The latter act individually and/or cooperatively, to sense and process the information needs posted by askers in their questions, so that these latter can be replied to in a timely and satisfactory manner through high-quality responses. Hitherto, the increasing relevance and popularity of CQA have fostered a wide spectrum of contributions from both academia and industry. Moreover, because of the growing number of such contributions straddling multiple research fields, CQA has rapidly developed into a multidisciplinary area that lies at the crossroads of natural language processing, recommender systems, social computing, knowledge representation, information retrieval, data mining, machine learning, and data science.

The aim of this Special Issue is to explore the latest advances in all tasks of CQA by collecting innovative developments, in which fundamental and practical aspects of interest are addressed. To this end, we solicit original contributions including theoretical as well as application-oriented studies. In particular, we encourage new interdisciplinary approaches which implement synergies among perspectives, developments, and progress across different fields. Additionally, we solicit novel studies in which multiple aspects of interests in CQA are considered jointly. We also welcome systematic reviews of the existing literature, with a special focus on the latest frontier of research as well as the open issues, unaddressed aspects, new trends, emerging applications, and future developments.

Finally, you are more than welcome to attend the “Second International Workshop on Expert Recommendation for Community Question Answering”(XPERT4CQA) (https://sites.google.com/icar.cnr.it/xpert4cqa-sdm2022/home), where the extensions of previously published works are invited, as long as these include at least 50% new material devoted to unprecedented and significant contributions, which must be clearly identified in the introduction.

The topics of interest for all submissions to this Special Issue include, but are not limited to:

  • Foundations, testing and best practices of innovative CQA methods, techniques, models, tools and systems. Design of new CQA systems and applications.
  • Knowledge creation, management and sharing in community-based questioning and answering.
  • Wisdom of the crowd. Collective intelligence. 
  • Case studies and analytics of CQA communities.
  • Evolutionary dynamics of questioning, answering, users and communities.
  • CQA and mobile environments.
  • Spatial, temporal and social context of mobile CQA users.
  • User context analysis and CQA.
  • Context-aware questioning and answering in mobile CQA environments.
  • Social sensing and CQA.
  • Mobile crowdsensing and CQA.
  • CQA user modeling and profiling: behavioral patterns, susceptibility, authority, expertise, reputation, influence, activity, willingness to reply and trustworthiness.
  • CQA content and topic modeling.
  • Knowledge representation and CQA.
  • Information diffusion and CQA.
  • Spread of misinformation/disinformation and CQA.
  • Promotion of active user participation.
  • Post quality and long-term value.
  • Exposure to posts.
  • User roles and CQA.
  • Post retrieval, suggestion and summarization.
  • CQA and web searches.
  • Question routing, expert finding, answerer recommendation.
  • Question routing for collaborative answering.
  • Tag recommendation.
Dr. Gianni Costa
Dr. Riccardo Ortale
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • CQA
  • User modeling
  • Content modeling
  • Question routing
  • Expert finding
  • Post quality
  • CQA context analysis
  • Mobile crowdsensing
  • Social sensing
  • Context-aware questioning and answering
  • Post quality
  • Post retrieval, suggestion and summarization
  • User roles in CQA
  • Information diffusion and CQA
  • Spread of misinformation/disinformation and CQA

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

18 pages, 2163 KiB  
Article
Deep Ensemble Fake News Detection Model Using Sequential Deep Learning Technique
by Abdullah Marish Ali, Fuad A. Ghaleb, Bander Ali Saleh Al-Rimy, Fawaz Jaber Alsolami and Asif Irshad Khan
Sensors 2022, 22(18), 6970; https://doi.org/10.3390/s22186970 - 15 Sep 2022
Cited by 16 | Viewed by 3497
Abstract
Recently, fake news has been widely spread through the Internet due to the increased use of social media for communication. Fake news has become a significant concern due to its harmful impact on individual attitudes and the community’s behavior. Researchers and social media [...] Read more.
Recently, fake news has been widely spread through the Internet due to the increased use of social media for communication. Fake news has become a significant concern due to its harmful impact on individual attitudes and the community’s behavior. Researchers and social media service providers have commonly utilized artificial intelligence techniques in the recent few years to rein in fake news propagation. However, fake news detection is challenging due to the use of political language and the high linguistic similarities between real and fake news. In addition, most news sentences are short, therefore finding valuable representative features that machine learning classifiers can use to distinguish between fake and authentic news is difficult because both false and legitimate news have comparable language traits. Existing fake news solutions suffer from low detection performance due to improper representation and model design. This study aims at improving the detection accuracy by proposing a deep ensemble fake news detection model using the sequential deep learning technique. The proposed model was constructed in three phases. In the first phase, features were extracted from news contents, preprocessed using natural language processing techniques, enriched using n-gram, and represented using the term frequency–inverse term frequency technique. In the second phase, an ensemble model based on deep learning was constructed as follows. Multiple binary classifiers were trained using sequential deep learning networks to extract the representative hidden features that could accurately classify news types. In the third phase, a multi-class classifier was constructed based on multilayer perceptron (MLP) and trained using the features extracted from the aggregated outputs of the deep learning-based binary classifiers for final classification. The two popular and well-known datasets (LIAR and ISOT) were used with different classifiers to benchmark the proposed model. Compared with the state-of-the-art models, which use deep contextualized representation with convolutional neural network (CNN), the proposed model shows significant improvements (2.41%) in the overall performance in terms of the F1score for the LIAR dataset, which is more challenging than other datasets. Meanwhile, the proposed model achieves 100% accuracy with ISOT. The study demonstrates that traditional features extracted from news content with proper model design outperform the existing models that were constructed based on text embedding techniques. Full article
Show Figures

Figure 1

Back to TopTop