International Journal of Web Based Communities (5 papers in press)
Mapping the agenda-setting theory, priming and the spiral of silence in Twitter accounts of political parties
by Marc Blasco-Duatis, Germà Coenders, Marc Saez, Nuria Fernández García, Isabel Ferin Cunha
Abstract: This paper presents the results of a content analysis of the official Twitter accounts of the main Spanish political parties (Partido Popular, Partido Socialista Obrero Español, Podemos, Ciudadanos and Izquierda Unida) carried out for the period of the 2015 Spanish general election. Compositional biplots are used for data visualisation. Unlike traditional approaches, compositional analysis in general, and the biplot in particular, emphasise the relative salience of issues within the agenda. This analysis sheds light on the agenda-setting theory and closely-related phenomena such as priming (based on associative-activation among a group of issues that are more influential than others) and the spiral of silence (the issues derived from the hierarchy process of agenda-setting that are omitted just after the election day).
Keywords: agenda-setting; biplot; compositional data; CoDa; political communication; priming; spiral of silence.
Investigating virtual communities of practice with social network analysis: guidelines from a systematic review of research
by Shazia K. Jan
Abstract: This paper presents a systematic review of research that uses social network analysis (SNA) to investigate virtual communities of practice (vCoPs). The review was driven by the lack of immediate value of time-consuming qualitative analyses typically conducted on vCoPs. The review seeks to assess the viability of SNA as a primary technique for structural investigation of vCoPs. Only 12 studies met the inclusion criteria for the review which evaluates and synthesises the use of SNA for exploring vCoPs. Overall, the review reveals that the application of SNA has been context specific and restrictive, therefore, the SNA in each study is neither comparable nor comprehensive. However, detailed evaluation and consolidation of the SNA in the studies enabled the development of specific guidelines for investigating vCoPs with SNA. By allowing timely and reliable analytics on online data, the SNA-based guidelines present valuable implications for ongoing analytics, design and facilitation of vCoPs.
Keywords: social network analysis; systematic review; guidelines; communities of practice; analytics; online data.
Racism and social media: a study in Indian context
by Naganna Chetty, Sreejith Alathur
Abstract: Racism is a kind of hatred behaviour, exhibited in written, verbal or physical form against the ethnicity or physical appearance of a group or an individual. Around the world, problematic behavioural incidents occur and in India, media often interpret it as towards people of colour or blacks. There was a lot of discussion about these incidents both online and offline, some groups consider that India is not free from racism and others view it is of misinformation processing. Therefore, there is a requirement of a system to evaluate and determine the possible scenarios towards racism in India. In this regard, using four different sets of keywords we created Twitter datasets. The data collected from social media are analysed to identify the polarity of content and the amount of racism using the software developed in R programming language. Contents are categorised in different polarities such as racist, non-racist and neutral.
Keywords: racism; hate; Twitter; black; African; Bollywood; India.
A web-based platform for strategy design in smart cities
by Aroua Taamallah, Maha Khemaja, Sami Faiz
Abstract: Decision makers adopt the smart city paradigm as a solution to current problems of cities. They call for innovative strategies to transform cities to smart ones. The development process of strategies is hard, complex and repetitive. Identifying such a process and providing a web platform for strategies development may facilitate such a process. We identify a generalised development process of strategies from the analysis of existing smart cities initiatives. Then, we propose a web-based platform that allows stakeholders to communicate, design and share strategies for smart cities development. The platform is based on the use of ontologies for knowledge structuring and formal description of strategies. The provided framework was tested by stakeholders. They design strategies in educational domain in Sousse, a Tunisian city. The preliminary result of the use of the framework shows that the latter has been useful for stakeholders in the process of strategies development.
Keywords: smart city; strategy; strategic planning; development process; web platform.
Lexicon-based Twitter sentiment analysis for vote share prediction using emoji and N-gram features
by Barkha Bansal, Sangeet Srivastava
Abstract: Recently, Twitter sentiment analysis (TSA) has been successfully employed to monitor and forecast elections in many studies. However, most of the existing studies rely on extracting sentiments from explicit textual features. Moreover, only few studies have included non-textual features such as emojis for election forecasts. In this study, we incorporated N-gram features to predict vote shares of 2017 Uttar Pradesh (UP) legislative elections. Also, sentiment distribution of tweets containing emojis was significantly different from tweets without emojis. Therefore, emoji sentiments were detected and incorporated to predict the vote shares. We collected more than 0.3 million tweets, wherein geo-tagging was applied on search keywords that were not exclusive to elections. We employed seven lexicons for labelling tweets and compared two methods to reduce prediction error: sentiment magnitude-based criteria and polarity of tweets. Results show that proposed method of incorporating N-gram features and emoji sentiments significantly decreases prediction error.
Keywords: Twitter sentiment analysis; TSA; emoji sentiment; geo-tag; electoral forecast; lexicon; N-grams.