Online Information Review

Ben-Abdallah, Emna; Boukadi, Khouloud; Hammami, Mohamed; Karray, Mohamed Hedi

2020 Online Information Review

doi: 10.1108/oir-06-2019-0207

The purpose of this paper is to analyze cloud reviews according to the end-user context and requirements.Design/methodology/approachpropose a comprehensive knowledge base composed of interconnected Web Ontology Language, namely, modular ontology for cloud service opinion analysis (SOPA). The SOPA knowledge base will be the basis of context-aware cloud service analysis using consumers' reviews. Moreover, the authors provide a framework to evaluate cloud services based on consumers' reviews opinions.FindingsThe findings show that there is a positive impact of personalizing the cloud service analysis by considering the reviewers' contexts in the performance of the framework. The authors also proved that the SOPA-based framework outperforms the available cloud review sites in term of precision, recall and F-measure.Research limitations/implicationsLimited information has been provided in the semantic web literature about the relationships between the different domains and the details on how that can be used to evaluate cloud service through consumer reviews and latent opinions. Furthermore, existing approaches are lacking lightweight and modular mechanisms which can be utilized to effectively exploit information existing in social media.Practical implicationsThe SOPA-based framework facilitates the opinion based service evaluation through a large number of consumer's reviews and assists the end-users in analyzing services as per their requirements and their own context.Originality/valueThe SOPA ontology is capable of representing the content of a product/service as well as its related opinions, which are extracted from the customer's reviews written in a specific context. Furthermore, the SOPA-based framework facilitates the opinion based service evaluation through a large number of consumer's reviews and assists the end-users in analyzing services as per their requirements and their own context.

Li, Yan; Wu, Ruijuan; Li, Dongjin

2020 Online Information Review

doi: 10.1108/oir-09-2018-0263

The purpose of this paper is to examine how subjective characteristics of social network sites (SNSs) affect consumers' positive and negative word-of-mouth (WOM) sharing.Design/methodology/approachThe data used for this study were obtained from an online survey with a sample size of 369 consumers. Structural equation modeling was performed to test hypotheses and examine the research questions.FindingsThe authors found that the perceived anonymity of an SNS is negatively correlated with its perceived interpersonal closeness of friends, and the number of friends in an SNS is positively correlated with its perceived interpersonal closeness of friends. With regard to positive WOM, the perceived anonymity of the SNS has a significant negative influence on consumers' WOM, and both perceived interpersonal closeness and the number of friends have a significant positive influence on consumers' WOM. But, in the case of negative WOM, only perceived interpersonal closeness of friends has a significant positive influence on consumers' WOM.Practical implicationsWhen attempting to promote positive WOM, marketers should choose consumers who possess the “right” subjective characteristics of SNSs (i.e. low anonymity, high interpersonal closeness of friends and a large number of friends). At the same time, marketers should monitor the emergence of consumers' negative WOM, especially those consumers who have a high level of interpersonal closeness of friends in SNSs, and respond to the content of negative WOM without delay.Originality/valueThis study investigates the influence that subjective characteristics of SNSs have on consumers' WOM sharing and therefore contributes to the literature on the antecedents of WOM generation and also contributes to the research that compares positive WOM with its negative counterpart.

O'Connell, David

2020 Online Information Review

doi: 10.1108/oir-11-2019-0358

The purpose of this paper to understand why some members of Congress have more Instagram followers, and why some Congressional Instagram posts receive more likes and comments.Design/methodology/approachThis study is based on a content analysis of every Instagram post shared by all members of Congress who were seated for the first six months of the 115th Congress (17,811 posts in all). Information was collected at both the account level, as well as at the level of the individual post. Variables were then created to predict a member's followers and a post's likes and comments using a series of regression models.FindingsThis paper finds that factors capturing real world influence best explain why some members have more followers on Instagram. Senators, members who have served longer in office, past or future presidential candidates, Congressional leaders and ideological extremists all had significantly more followers. This paper also shows that personal content such as family photos, personal photos, selfies and pet photos produces significantly more user responses, while impersonal content like text based posts produces fewer.Practical implicationsThis paper offers a general understanding of how anyone might maximize their user engagement on Instagram.Originality/valueLittle published research has studied how politicians use Instagram. This paper expands previous work examining influence on Twitter and Facebook. Further, these findings shed light on broader issues, including how social media reinforces existing power biases, and on the increasing trend towards personalization in American politics.

Iqbal Khan, Shahid; Bilal, Ahmad Raza; Ahmad, Bilal

2020 Online Information Review

doi: 10.1108/oir-12-2019-0375

The purpose of this study is to investigate the impact of page-specific factors such as page language, posting frequency and community size on online engagement in the context of social media pages of news channels in Pakistan.Design/methodology/approachFor this research, official Facebook pages of news channels in Pakistan were defined as the target population. Secondary data were obtained from the Facebook pages of 28 news channels in Pakistan. For the selected period between August and September 2019, a total of 420 cases were obtained and manually entered in SPSS 21 for analysis. Tweedie estimation was run to check the proposed hypotheses.FindingsResults show that English pages are more engaging than Urdu. Additionally, posting frequency and community size have a negative relationship with online engagement.Practical implicationsThe findings of the study suggest that administrators of social media pages of news channels should target English news readers more than Urdu news readers. Additionally, they should manage a low posting frequency so that readers may not get irritated. Administrators should not sponsor their pages to expand community size on a single page. Instead, they may opt to build a separate page for each news category with smaller community size.Originality/valueWhile previous studies have discussed the post-specific factors of engagement, this study has checked the impact of page-specific factors such as page language, posting frequency and community size on online engagement.

Quan, Thanh-Tho; Mai, Duc-Trung; Tran, Thanh-Duy

2020 Online Information Review

doi: 10.1108/oir-02-2019-0062

This paper proposes an approach to identify categorical influencers (i.e. influencers is the person who is active in the targeted categories) in social media channels. Categorical influencers are important for media marketing but to automatically detect them remains a challenge.Design/methodology/approachWe deployed the emerging deep learning approaches. Precisely, we used word embedding to encode semantic information of words occurring in the common microtext of social media and used variational autoencoder (VAE) to approximate the topic modeling process, through which the active categories of influencers are automatically detected. We developed a system known as Categorical Influencer Detection (CID) to realize those ideas.FindingsThe approach of using VAE to simulate the Latent Dirichlet Allocation (LDA) process can effectively handle the task of topic modeling on the vast dataset of microtext on social media channels.Research limitations/implicationsThis work has two major contributions. The first one is the detection of topics on microtexts using deep learning approach. The second is the identification of categorical influencers in social media.Practical implicationsThis work can help brands to do digital marketing on social media effectively by approaching appropriate influencers. A real case study is given to illustrate it.Originality/valueIn this paper, we discuss an approach to automatically identify the active categories of influencers by performing topic detection from the microtext related to the influencers in social media channels. To do so, we use deep learning to approximate the topic modeling process of the conventional approaches (such as LDA).

Thelwall, Mike; Papas, Eleanor-Rose; Nyakoojo, Zena; Allen, Liz; Weigert, Verena

2020 Online Information Review

doi: 10.1108/oir-11-2019-0347

Peer reviewer evaluations of academic papers are known to be variable in content and overall judgements but are important academic publishing safeguards. This article introduces a sentiment analysis program, PeerJudge, to detect praise and criticism in peer evaluations. It is designed to support editorial management decisions and reviewers in the scholarly publishing process and for grant funding decision workflows. The initial version of PeerJudge is tailored for reviews from F1000Research's open peer review publishing platform.Design/methodology/approachPeerJudge uses a lexical sentiment analysis approach with a human-coded initial sentiment lexicon and machine learning adjustments and additions. It was built with an F1000Research development corpus and evaluated on a different F1000Research test corpus using reviewer ratings.FindingsPeerJudge can predict F1000Research judgements from negative evaluations in reviewers' comments more accurately than baseline approaches, although not from positive reviewer comments, which seem to be largely unrelated to reviewer decisions. Within the F1000Research mode of post-publication peer review, the absence of any detected negative comments is a reliable indicator that an article will be ‘approved’, but the presence of moderately negative comments could lead to either an approved or approved with reservations decision.Originality/valuePeerJudge is the first transparent AI approach to peer review sentiment detection. It may be used to identify anomalous reviews with text potentially not matching judgements for individual checks or systematic bias assessments.

Ebrahimzadeh, Sanam; Rezaei Sharifabadi, Saeed; Karbala Aghaie Kamran, Masoumeh; Dalkir, Kimiz

2020 Online Information Review

doi: 10.1108/oir-12-2019-0380

The purpose of this paper is to identify the triggers, strategies and outcomes of collaborative information-seeking behaviours of researchers on the ResearchGate social networking site.Design/methodology/approachData were collected from the population of researchers who use ResearchGate. The sample was limited to the Ph.D. students and assistant professors in the library and information science domain. Qualitative interviews were used for data collection.FindingsBased on the findings of the study, informal communications and complex information needs lead to a decision to use collaborative information-seeking behaviour. Also, easy access to sources of information and finding relevant information were the major positive factors contributing to collaborative information-seeking behaviour of the ResearchGate users. Users moved from collaborative Q&A strategies to sharing information, synthesising information and networking strategies based on their needs. Analysis of information-seeking behaviour showed that ResearchGate users bridged the information gap by internalizing new knowledge, making collaborative decisions and increasing their work's visibility.Originality/valueAs one of the initial studies on the collaborative information-seeking behaviour of ResearchGate users, this study provides a holistic picture of different triggers that affect researchers' information-seeking on ResearchGate.

Mehmood, Yasir; Balakrishnan, Vimala

2020 Online Information Review

doi: 10.1108/oir-10-2018-0295

Research on sentiment analysis were mostly conducted on product and services, resulting in scarcity of studies focusing on social issues, which may require different mechanisms due to the nature of the issue itself. This paper aims to address this gap by developing an enhanced lexicon-based approach.Design/methodology/approachAn enhanced lexicon-based approach was employed using General Inquirer, incorporated with multi-level grammatical dependencies and the role of verb. Data on illegal immigration were gathered from Twitter for a period of three months, resulting in 694,141 tweets. Of these, 2,500 tweets were segregated into two datasets for evaluation purposes after filtering and pre-processing.FindingsThe enhanced approach outperformed ten online sentiment analysis tools with an overall accuracy of 81.4 and 82.3% for dataset 1 and 2, respectively as opposed to ten other sentiment analysis tools.Originality/valueThe study is novel in the sense that data pertaining to a social issue were used instead of products and services, which require different mechanism due to the nature of the issue itself.

Zhou, Tao

2020 Online Information Review

doi: 10.1108/oir-09-2019-0298

The purpose of this research is to examine the effect of information privacy concern on users' social shopping intention.Design/methodology/approachBased on the 340 valid responses collected from a survey, structural equation modeling (SEM) was employed to examine the research model.FindingsThe results indicated that while disposition to privacy positively affects privacy concern, both reputation and laws negatively affect privacy concern, which in turn decreases social shopping intention. In addition, trust partially mediates the effect of privacy concern on social shopping intention.Research limitations/implicationsThe results imply that social commerce companies need to mitigate users' privacy concern in order to facilitate their shopping behavior.Originality/valueThis research disclosed that privacy concern receives a tripartite influence from users (disposition to privacy), platforms (reputation) and governments (laws). The results help us gain a complete understanding of information privacy concern mitigation in social shopping.

Ma, Xiaoyue; Ma, Hao

2020 Online Information Review

doi: 10.1108/oir-12-2019-0372

Graphic-based tag clouds aim to visually represent tag content and tag structure, and then to better represent tagged information for later search. However, few studies have clarified the features among varied visualization approaches involved in graphic-based tag clouds and compared them for the purpose of information search.Design/methodology/approachAfter reviewing four kinds of graphic-based tag clouds, an experimental demonstration was conducted in our study to verify how user performs in information search for a general seeking task by using them. Precision ratio, recall ratio, clicks on search and time for search were four variables tested in the experiment. Also, two supplementary tests were respectively carried out to manifest how graphic-based tag clouds contributed to the identification of target tags and tag clusters.FindingsThe experimental results showed that compared to tag content visual tag structure was more important to find related tags from tag clouds for information search. In addition, tag clouds that visually represented the semantic relationships within tags could make user more confident about their search result and carry out a shorter learning process during searching, which signified a tag-based information search path when visual elements were applied.Originality/valueThis research is one of the first to illustrate systematically the graphic-based tag clouds and their impacts on information search. The research findings could suggest on how to build up more effective and interactive tag clouds and make proposition for the design of search user interface by using graphic-based tag clouds.