The Experts below are selected from a list of 365172 Experts worldwide ranked by ideXlab platform
Minh-tien Nguyen - One of the best experts on this subject based on the ideXlab platform.
-
Social context summarization using User-Generated Content and third-party sources
Knowledge-Based Systems, 2018Co-Authors: Minh-tien Nguyen, Duc-vu Tran, Le-minh NguyenAbstract:Abstract In the context of social media, users mutually share their interests of an event mentioned in a Web document. Its Content can also be found in different news providers with a writing variation. This paper presents a framework which exploits the support of social context (User-Generated Content such as comments or tweets and third-party sources such as relevant documents retrieved from a search engine) to extract high-quality summaries. The extraction was formulated in two steps: sentence scoring and selection. The scoring is modeled as a learning to rank problem, which employs Ranking SVM to mutually exploits sentences, User-Generated Content, and third-party sources in the form of features to cover summary aspects. For the selection, summaries are extracted by using a score-based or voting method. For evaluation, three datasets of sentence and highlight extraction in two languages were taken as a case study. Experimental results indicate that by integrating User-Generated Content and third-party sources, our framework obtains improvements of ROUGE-scores over state-of-the-art methods for single-document summarization.
-
Exploiting User-Generated Content to Enrich Web Document Summarization
International Journal on Artificial Intelligence Tools, 2017Co-Authors: Minh-tien Nguyen, Duc-vu Tran, Chien-xuan Tran, Minh-le NguyenAbstract:User-Generated Content such as comments or tweets (also called by social information) following a Web document provides additional information for enriching the Content of an event mentioned in sentences. This paper presents a framework named SoSVMRank, which integrates the User-Generated Content of a Web document to generate a highquality summarization. In order to do that, the summarization was formulated as a learning to rank task, in which comments or tweets are exploited to support sentences in a mutual reinforcement fashion. To model sentence-comment (or tweet) relation, a set of local and social features are proposed. After ranking, top m ranked sentences and comments (or tweets) are selected as the summarization. To validate the efficiency of our framework, sentence and story highlight extraction tasks were taken as a case study on three datasets in two languages, English and Vietnamese. Experimental results indicate that: (i) our new features improve the summary performance of the framework in term of ROUGE-scores compared to state-of-the-art baselines and (ii) the integration of User-Generated Content benefits single-document summarization.
-
Exploiting User-Generated Content to Enrich Web Document Summarization
International Journal on Artificial Intelligence Tools, 2017Co-Authors: Minh-tien Nguyen, Duc-vu Tran, Chien-xuan Tran, Minh Le NguyenAbstract:User-Generated Content such as comments or tweets (also called by social information) following a Web document provides additional information for enriching the Content of an event mentioned in sentences. This paper presents a framework named SoSVMRank, which integrates the User-Generated Content of a Web document to generate a highquality summarization. In order to do that, the summarization was formulated as a learning to rank task, in which comments or tweets are exploited to support sentences in a mutual reinforcement fashion. To model sentence-comment (or tweet) relation, a set of local and social features are proposed. After ranking, top m ranked sentences and comments (or tweets) are selected as the summarization. To validate the efficiency of our framework, sentence and story highlight extraction tasks were taken as a case study on three datasets in two languages, English and Vietnamese. Experimental results indicate that: (i) our new features improve the summary performance of the framework in te...
Sherali Zeadally - One of the best experts on this subject based on the ideXlab platform.
-
The Challenge of Improving Credibility of User-Generated Content in Online Social Networks
Journal of Data and Information Quality, 2016Co-Authors: Giannis Haralabopoulos, Ioannis Anagnostopoulos, Sherali ZeadallyAbstract:In every environment of information exchange, Information Quality (IQ) is considered one of the most important issues. Studies in Online Social Networks (OSNs) analyze a number of related subjects that span both theoretical and practical aspects, from data quality identification and simple attribute classification to quality assessment models for various social environments. Among several factors that affect information quality in online social networks is the credibility of User-Generated Content. To address this challenge, some proposed solutions include community-based evaluation and labeling of User-Generated Content in terms of accuracy, clarity, and timeliness, along with well-established real-time data mining techniques.
Chunli Liu - One of the best experts on this subject based on the ideXlab platform.
-
DSC - The Impact of Personality on User-Generated Content in Online Social Networks.
2019 IEEE Fourth International Conference on Data Science in Cyberspace (DSC), 2019Co-Authors: Jianshan Sun, Liu Yajue, Chunhua Sun, Chunli LiuAbstract:The rapid promotion of online social networks and the unprecedented enthusiasm of Internet users have led to a sharp increase in User-Generated Content. Understanding the user behavior behind various User-Generated Content is a challenging task. The impact of a user's personality traits on User-Generated Content is an issue we want to explore. This article combines the user's personality survey data with Facebook's User-Generated Content data. We explore User-Generated Content from four aspects: topic preferences, expression patterns, sentiment states and cognition styles. The experimental results show that in online social networks, personality traits will affect the topic preferences, expression patterns, sentiment states and cognition styles from User-Generated Content, and the influence of different personality traits is different.
Duc-vu Tran - One of the best experts on this subject based on the ideXlab platform.
-
Social context summarization using User-Generated Content and third-party sources
Knowledge-Based Systems, 2018Co-Authors: Minh-tien Nguyen, Duc-vu Tran, Le-minh NguyenAbstract:Abstract In the context of social media, users mutually share their interests of an event mentioned in a Web document. Its Content can also be found in different news providers with a writing variation. This paper presents a framework which exploits the support of social context (User-Generated Content such as comments or tweets and third-party sources such as relevant documents retrieved from a search engine) to extract high-quality summaries. The extraction was formulated in two steps: sentence scoring and selection. The scoring is modeled as a learning to rank problem, which employs Ranking SVM to mutually exploits sentences, User-Generated Content, and third-party sources in the form of features to cover summary aspects. For the selection, summaries are extracted by using a score-based or voting method. For evaluation, three datasets of sentence and highlight extraction in two languages were taken as a case study. Experimental results indicate that by integrating User-Generated Content and third-party sources, our framework obtains improvements of ROUGE-scores over state-of-the-art methods for single-document summarization.
-
Exploiting User-Generated Content to Enrich Web Document Summarization
International Journal on Artificial Intelligence Tools, 2017Co-Authors: Minh-tien Nguyen, Duc-vu Tran, Chien-xuan Tran, Minh-le NguyenAbstract:User-Generated Content such as comments or tweets (also called by social information) following a Web document provides additional information for enriching the Content of an event mentioned in sentences. This paper presents a framework named SoSVMRank, which integrates the User-Generated Content of a Web document to generate a highquality summarization. In order to do that, the summarization was formulated as a learning to rank task, in which comments or tweets are exploited to support sentences in a mutual reinforcement fashion. To model sentence-comment (or tweet) relation, a set of local and social features are proposed. After ranking, top m ranked sentences and comments (or tweets) are selected as the summarization. To validate the efficiency of our framework, sentence and story highlight extraction tasks were taken as a case study on three datasets in two languages, English and Vietnamese. Experimental results indicate that: (i) our new features improve the summary performance of the framework in term of ROUGE-scores compared to state-of-the-art baselines and (ii) the integration of User-Generated Content benefits single-document summarization.
-
Exploiting User-Generated Content to Enrich Web Document Summarization
International Journal on Artificial Intelligence Tools, 2017Co-Authors: Minh-tien Nguyen, Duc-vu Tran, Chien-xuan Tran, Minh Le NguyenAbstract:User-Generated Content such as comments or tweets (also called by social information) following a Web document provides additional information for enriching the Content of an event mentioned in sentences. This paper presents a framework named SoSVMRank, which integrates the User-Generated Content of a Web document to generate a highquality summarization. In order to do that, the summarization was formulated as a learning to rank task, in which comments or tweets are exploited to support sentences in a mutual reinforcement fashion. To model sentence-comment (or tweet) relation, a set of local and social features are proposed. After ranking, top m ranked sentences and comments (or tweets) are selected as the summarization. To validate the efficiency of our framework, sentence and story highlight extraction tasks were taken as a case study on three datasets in two languages, English and Vietnamese. Experimental results indicate that: (i) our new features improve the summary performance of the framework in te...
Jayan Chirayath Kurian - One of the best experts on this subject based on the ideXlab platform.
-
User-Generated Content on the Facebook page of an emergency management agency: A thematic analysis
Online Information Review, 2017Co-Authors: Jayan Chirayath Kurian, Blooma JohnAbstract:Purpose The purpose of this study is to explore themes eventuating from the User-Generated Content posted by users on the Facebook page of an emergency management agency. Design/methodology/approach An information classification framework was used to classify User-Generated Content posted by users including all of the Content posted during a six month period (January to June, 2015). The posts were read and analysed thematically to determine the overarching themes evident across the entire collection of user posts. Findings The results of the analysis demonstrate that the key themes that eventuate from the User-Generated Content posted are “Self-preparedness”, “Emergency signalling solutions”, “Unsurpassable companion”, “Aftermath of an emergency”, and “Gratitude towards emergency management staff”. Major User-Generated Content identified among these themes are status-update, criticism, recommendation, and request. Research limitations/implications This study contributes to theory on the development of key...
-
User-Generated Content on Facebook: Implications from the perspective of two organisations
First Monday, 2016Co-Authors: Jayan Chirayath KurianAbstract:The purpose of this study is to examine the implications (user benefits and costs) of User-Generated Content posted by users on Facebook from an organisational perspective. Though motivations to use social networking sites are widely researched and published, studies on implications eventuating from different types of Content posted by users on social networking sites is sparse. Hence, this study addresses the gap in literature by an interpretive analysis of User-Generated Content posted by users on the Facebook of two organisations. The Content posted by users is classified using an information classification framework for social networking sites. Implications eventuating from the classified User-Generated Content to individuals and organisations are established using thematic analysis. The results of analysis demonstrate that the major types of User-Generated Content posted in the social information category are requests, criticism, greetings, status updates, and announcements. The theoretical implications in terms of user benefits are information seeking, relationship building, coordination and collaboration, identity construction and knowledge dissemination whereas social conflict is a major cost to users. The practical implications are understood in terms of technical assistance, supporting projects that extend open access repository initiatives, collaboration and building capacity among repository users, user community development, marketing and communication as well as accomplishing the core principles of the National Strategy for Disaster Resilience. This study also leads to considerable gains for users and designers of social networking sites by identifying the different types of User-Generated Content so that social networking sites can be used as a beneficial tool maximizing its implications.
-
PACIS - Implications of user generated Content on Facebook
2015Co-Authors: Jayan Chirayath KurianAbstract:The purpose of this study is to examine the implications (user benefits and costs) of user generated Content posted by users on Facebook to individual users. Although motivations to use social networking sites are widely researched and published, studies on implications of information on social networking sites is sparse. Hence, this study addresses this gap by an interpretive analysis of user generated Content posted by users on Facebook. Content posted by a selected number of users on Facebook is classified based on an information classification framework. Implications eventuating from the classified user generated Content to individual users are established using thematic analysis. Findings indicate that Self presentation and relationship building are the major user benefits eventuating from basic user information, whereas loss of privacy, security risk, and identity theft are the major user costs. Users entail professional career development by posting information on user's education. Employment details of user entail benefits of professional career development and impression management. On the other hand, posting textual communication entails benefits of impression management, enjoyment, and relationship building, whereas costs include social conflict and emotional distress. Findings of this study add to the theory on implications of user generated Content posted by users on Facebook.
