Public opinion dissemination on mobile internet- a case of Ebola

Influencing Factors on College Students' Willingness to Spread Internet Public Opinion: Analysis Based on COVID-19 Data in China

Following COVID-19 outbreak, Internet public opinion has tended to proliferate. From a theoretical perspective, however, the spread law of Internet public opinion in major epidemic prevention and control may provide optimization strategies on how best to channel Internet public opinion. Specifically, this article aims at exploring key factors affecting our theoretical understanding on the spread of Internet public opinion on a major epidemic situation amongst college students. A questionnaire survey on college students was conducted via online research data collection platform located in Changsha, China, amassing three hundred and nineteen valid questionnaires. Smart PLS was applied to verify a theoretical model vis-à-vis the reliability and validity of the measuring instrument. Results show that adult attachment and social motivation have significant positive influences on the consciousness of social participation. Evidently, adult attachment, emotional orientation and risk perception also have significant positive influences on emotional motivation. Emotional motivation plays a mediating role in the relationship between affective disposition and dissemination willingness. Additionally, social motivation, consciousness of social participation and emotional motivation significantly influence one's dissemination willingness in a positive way. The consciousness of social participation plays a mediating role in the relationship between social motivation and dissemination willingness. Social motivation plays a moderating role in the relationship between risk perception and dissemination willingness. Altogether, theoretical rationalization to enhance understanding and guide the initiation and spread of Internet public opinion of major public health emergencies accurately has now been provided by this work.

Factors influencing college students’ behaviours of spreading internet public opinions on emergencies in universities

Purpose

This study aims to explore the influencing factors on college students’ behaviours of spreading Internet public opinion on emergencies in colleges and universities. This study provides a reference for these institutions to cope with and reduce the influence of Internet public opinion on emergencies and maintain their normal teaching order.

Design/methodology/approach

In this study, a research model by using motivation theory and design a questionnaire on the basis of relevant literature are constructed. This paper surveys college students and collects a total of 317 valid questionnaires. On the basis of the reliability and validity of the questionnaire, this study verifies the proposed model by using Smart PLS.

Findings

The results show that social motivation and information source preference have significant positive influences on college students’ willingness to spread Internet public opinion on emergencies in colleges and universities. Moreover, information source preference has a significant moderating effect on the relationship between social motivation and dissemination willingness. If college students’ information source preference is high, then the moderating effect is significant. The extent of college students’ interaction and involvement has a significantly positive influence on their trust in the dissemination platform for Internet public opinion on emergencies in colleges and universities. Egoism has a significantly positive influence on the social motivation of college students to spread Internet public opinion on emergencies in colleges and universities. Involvement degree has a significant moderating effect on the relationship between social motivation and trust. If college students’ involvement degree is low, then the moderating effect is significant. Thus, when the involvement of college students in Internet public opinion on emergencies in colleges and universities is low, the influence of social motivation on trust is great.

Originality/value

This study increases the influencing factors in the literature on Internet public opinion, enriches the research theory of Internet public opinion on emergencies in colleges and universities and expands the application scope of the theory of social motivation. The conclusion provides guidance for colleges and students to govern Internet public opinion on emergencies and improve the ability of these institutions in dealing with Internet public opinion on emergencies.

Aspect context aware sentiment classification of online consumer reviews

Purpose

Aspect based sentiment classification is valuable for providing deeper insight into online consumer reviews (OCR). However, the majority of the previous studies explicitly determine the orientation of aspect related sentiment bearing word and overlook the aspect-context. Therefore, this paper aims to propose an aspect-context aware sentiment classification of OCR for deeper and more accurate insights.

Design/methodology/approach

In the proposed methodology, first, aspect descriptions and sentiment bearing words are extracted. Then, the skip-gram model is used to extract the first set of features to capture contextual information. For the second category of features, cosine similarity is used between a pre-defined seed word list and aspects, to capture aspect context sensitive sentiments. The third set of features includes weighted word vectors using term frequency-inverse document frequency. After concatenating features, ensemble classifier is used using three base classifiers.

Findings

Experimental results on two real-world data sets with variable lengths, acquired from Amazon.com and TripAdvisor.com, show that the advised ensemble approach significantly outperforms sentiment classification accuracy of state-of-the-art and baseline methods.

Originality/value

This method is capable of capturing the correct sentiment of ambiguous words and other special words by extracting aspect-context using word vector similarity instead of expensive lexical resources, and hence, shows superior performance in terms of accuracy as compared to other methods.