Topic Popularity Research Articles

A New Popularity Prediction Model for Detection of Trending Topics based on Support Vector Machine over Online Social Networking

Social network is the most reliable platform to share data. It produces a huge number of subjects each day. Online media is critical for business associations to learn the popularity of these themes as fast as could be expected. This paper is centered around the investigation of five distinctive existing trending detection methods, such as The Prediction Model based on SVM, Multi Linear Model, Dual Attention Model, Self Attention based Model, Trust Prediction Model, etc. But a few upsides and downsides are seen in these methods. These methodologies have been analyzed to address the limits of the trending topic popularity prediction such as video lifetime, burst and evolution pattern, execution, error rate, time, overhead, throughput, delay, limit, and so on. In this paper, “Rapid Miner” tool is used to implement the proposed method. The correlation matrix is used for pattern detection, then clustering is performed over the output of the correlation matrix and obtains the data in cluster format i.e. in similar sequence, and again random clustering technique is performed over previous K-means clustering result, in which, it simply divides topic information into time slices which are utilized as a unit, and such units are provides to the two unique detectors, for example, lifetime and bursty detector. At last, SVM classification predicts the outcomes in the type of a "Trending Topic" and a "Non-Trending Topic". The proposed strategy is “Detection of the Trending Topic” which dependent on SVM. The proposed method recognizes the lifetime of recordings, bustiness of recordings, and evolution pattern. It decreases the mistake rate, time, overhead, delay, and enhances the precision, execution, use of mistake rate as a measurement, throughput, ability to improve the trending subject identification rate, etc. This proposed strategy concentrates on a trending subject and fake data over OSN.

HK–SEIR model of public opinion evolution based on communication factors

Microblog, with its good interaction and convenient dissemination, has become the main platform for public opinion dissemination. How to discover the law of public opinion dissemination, and to identify the public opinion accurately have become the hot researches. In this paper, we define the user influence, topic popularity, topic interest to analysis the process of opinions fusion among the users under the interest and confidence threshold. We propose a new public opinion evolution HK–SEIR model which combines the opinion fusion HK and the epidemic transmission SEIR models. Firstly, the topic interest degree is added to the opinion fusion HK model, and the interaction behavior between the users under the interest and confidence threshold is analyzed. Then, we calculate the probability of topic propagation caused by the interaction of opinions between users under group pressure, and the probability that users change from the infected state to the removed state under topic popularity. Finally, we analyze the changes of the susceptible, exposed, infected and removed states in the process of public opinion communication. The experiment proves that the HK–SEIR model is closer to the work-rest rules of public opinion communication than SEIR, SIR model. The density peak time is closer to the peak of real public opinion communication. We find that the user interest is the main factor influencing the public opinion dissemination after the interaction of user opinions fusion reaches a certain degree. The negative public opinion of the higher proportion can easily reach the peak of public opinion propagation.

Measuring topic network centrality for identifying technology and technological development in online communities

Online communities are a rapidly growing knowledge repository that provides scholarly research, technical discussion, and social interactivity. This abundance of online information increases the difficulty of keeping up with new developments difficult for researchers and practitioners. Thus, we introduced a novel method that analyses both knowledge and social sentiment within the online community to discover the topical coverage of emerging technology and trace technological trends. The method utilizes the Weibull distribution and Shannon entropy to measure and link social sentiment with technological topics. Based on question-and-answer and social sentiment data from Zhihu, which is an online question and answer (Q&A) community with high-profile entrepreneurs and public intellectuals, we built an undirected weighting network and measured the centrality of nodes for technology identification. An empirical study on artificial intelligence technology trends supported by expert knowledge-based evaluation and cognition provides sufficient evidence of the method's ability to identify technology. We found that the social sentiment of hot technological topics presents a long-tailed distribution statistical pattern. High similarity between the topic popularity and emerging technology development trends appears in the online community. Finally, we discuss the findings in various professional fields that are widely applied to discover and track hot technological topics.

Can we 'feel' the temperature of knowledge? Modelling scientific popularity dynamics via thermodynamics.

Just like everything in nature, scientific topics flourish and perish. While existing literature well captures article’s life-cycle via citation patterns, little is known about how scientific popularity and impact evolves for a specific topic. It would be most intuitive if we could ‘feel’ topic’s activity just as we perceive the weather by temperature. Here, we conceive knowledge temperature to quantify topic overall popularity and impact through citation network dynamics. Knowledge temperature includes 2 parts. One part depicts lasting impact by assessing knowledge accumulation with an analogy between topic evolution and isobaric expansion. The other part gauges temporal changes in knowledge structure, an embodiment of short-term popularity, through the rate of entropy change with internal energy, 2 thermodynamic variables approximated via node degree and edge number. Our analysis of representative topics with size ranging from 1000 to over 30000 articles reveals that the key to flourishing is topics’ ability in accumulating useful information for future knowledge generation. Topics particularly experience temperature surges when their knowledge structure is altered by influential articles. The spike is especially obvious when there appears a single non-trivial novel research focus or merging in topic structure. Overall, knowledge temperature manifests topics’ distinct evolutionary cycles.

What Do Practitioners Discuss about IoT and Industry 4.0 Related Technologies? Characterization and Identification of IoT and Industry 4.0 Categories in Stack Overflow Discussions

Internet of Things and Industry 4.0–related discussions have become increasingly prevalent on several online Q&A websites in recent years. Analyzing and understanding such discussions could provide practitioners with more insights into various trends in the evolution of topics of interest and help different research communities, including software development and industrial sectors, better understand the needs and challenges facing practitioners as they operate in these fields. We conduct an exploratory study to capture and compare the popularity as well as the effect of the discussion topics on the domain across such communities. We use extracted data from popular online Q&A websites, such as Stack Exchange, and investigate 176,819 posts to investigate what practitioners are asking and looking for. We also use Machine Learning for Language Toolkit (MALLET) based–Latent Dirichlet Allocation (LDA) topic models to help summarize Internet of Things/Industry 4.0–related questions, identify the most challenging popular related issues, explore specific issues of the Internet of Things/Industry 4.0, and investigate the types of questions that practitioners ask about. We summarize all the topics into various categories and evaluate the popularity and difficulty of various topics as well. Our findings help to highlight the challenges facing the Internet of Things/Industry 4.0 practitioners which in the future would require more attention from various research and software development communities and develop new approaches to analyzing questions posed on various Q&A forums.

Cultural Modernisation And Film Industry: Naked Facts From IMDB

This paper focuses on the relationship between film content and human values in Europe. Our research fills in two research gaps. For one thing, it reveals the links between people’s values and visual cultural production that can showcase the effects of changing values on culture. The other part of our research concerns the use of the Internet Movie Database (IMDb) as a data set reflecting changes in modern societies. We track the changes in film topics provided by the IMDb and European Values Study (EVS) data to see how the changes in people’s values are linked to the popularity of related topics. Our special focus lies on the link between choice values and the probability of nudity depiction in films. The sample contained all European countries across 1960-2013. Using multilevel regression analysis, we found that the probability of female nudity is associated with the level of choice values, whereas the male nudity is more likely to appear in films related to the topic of homosexuality.

An Empirical Study of Bioinformatics Topics in Online Forum Discussions

In this paper, we aim to understand the topics discussed by bioinformatics practitioners in Stack Exchange sites. We downloaded all bioinformatics posts (questions and accepted answers) from four Stack Exchange Q&A sites (Stack Overflow, Biology, Cross-Validated, and Bioinformatics). Then we applied topic modeling on each site data. We labeled the topics and grouped those into high level categories. We analyzed the topics further by determining their popularity, difficulty, and evolution. We have made a comparative analysis of the topics across the different studied sites. We found 14 topics in Stack Overflow that are grouped into six categories. The number of new bioinformatics questions is steadily increasing over time in Stack Overflow for each topic category. Topics related to sequence analysis and pattern detection are the most popular as well as the most difficult to get an accepted answer. Most of the discussion posts are ‘how’ type questions, i.e., the practitioners were looking for solutions. While topics like biodata processing are found in multiple Stack Exchange sites, other topics (e.g., gene evolution analysis) are found in specialized sites (e.g., Biology). These findings show the need for consulting multiple related sites in Stack Exchange to learn interdisciplinary fields like bioinformatics. The tradeoff between popularity and difficulty of the bioinformatics topics highlights that bioinformatics practitioners need documentation and better tool support. The bioinformatics researchers, organizations, and practitioners can look into our results to prioritize the specific areas that need more focus for improvement.

A time-sensitive model to predict topic popularity in news providers1

The volume of news increases everyday, triggering competition for users’ attention. Predicting which topics will become trendy has many applications in domains like marketing or politics, where it is crucial to anticipate how much interest a product or a person will attract. We propose a model for representing topic popularity behavior across time and to predict if a topic will become trendy in the future. Furthermore, we tested our proposal on a real data set from Yahoo News and analyzed the performance of various classifiers for the topic popularity prediction task. Experiments confirmed the validity of the proposed model.

Predictability limit of partially observed systems

Applications from finance to epidemiology and cyber-security require accurate forecasts of dynamic phenomena, which are often only partially observed. We demonstrate that a system’s predictability degrades as a function of temporal sampling, regardless of the adopted forecasting model. We quantify the loss of predictability due to sampling, and show that it cannot be recovered by using external signals. We validate the generality of our theoretical findings in real-world partially observed systems representing infectious disease outbreaks, online discussions, and software development projects. On a variety of prediction tasks—forecasting new infections, the popularity of topics in online discussions, or interest in cryptocurrency projects—predictability irrecoverably decays as a function of sampling, unveiling predictability limits in partially observed systems.

The COVID-19 research landscape: Measuring topics and collaborations using scientific literature.

Objectives:The Coronavirus Disease 2019 (COVID-19) caused heavy burdens and brought tremendous challenges to global public health. This study aimed to investigate collaboration relationships, research topics, and research trends on COVID-19 using scientific literature.Method:COVID-19-related articles published from January 1 to July 1, 2020 were retrieved from PubMed database. A total of 27,370 articles were included. Excel 2010, Medical Text Indexer (MTI), VOSviewer, and D3.js were used to summarize bibliometric features.Results:The number of the COVID-19 research publications has been continuously increasing after its break. United States was the most productive and active country for COVID-19 research, with the largest number of publications and collaboration relationships. Huazhong University of Science and Technology from China was the most productive institute on the number of publications, and University of Toronto from Canada ranked as Top 1 institute for global research collaboration. Four key research topics were identified, of which the topic of epidemiology and public health interventions has gathered highest attentions. Topic of virus infection and immunity has been more focused during the early stage of COVID-19 outbreak compared with later stage. The topic popularity of clinical symptoms and diagnosis has been steady.Conclusions:Our topic analysis results revealed that the study of drug treatment was insufficient. To achieve critical breakthroughs of this research area, more interdisciplinary, multi-institutional, and global research collaborations are needed.

Prediction of online topics’ popularity patterns

Popularity prediction of online contents is always a tool of emergency management, business decision-making, and public opinion monitoring. Most previous work has made efforts to predict the volumes or levels of popularity, but patterns of popularity evolution are remaining largely unexplored. Actually, topic popularity patterns can offer more detailed information for event detection and early warning. In this article, we proposed an effective method to discover and predict the popularity patterns of topics on the Internet which combined clustering and classification models. This method does not rely on the early time data of topic propagation, so it can predict the future popularity pattern at the initial stage of topic releasing. First, we chose a time series clustering algorithm K-SC to obtain basic types of topic popularity patterns. Then, through acquiring and evaluating multiple features related to the topics including publisher features, outward characteristics of content and textual ones, we built the prediction model of topic popularity patterns based on machine learning methods. The experimental results show that it is suitable to cluster four basic patterns of topic popularity from the experimental data. What’s more, making use of certain initial characteristics, Decision Tree model can effectively predict the popularity pattern of a newly released topic, with an accuracy of 89.4%.

Indicator Selection for Topic Popularity Definition Based on AHP and Deep Learning Models

Purpose. The purpose of this article is to predict the topic popularity on the social network accurately. Indicator selection model for a new definition of topic popularity with degree of grey incidence (DGI) is undertook based on an improved analytic hierarchy process (AHP). Design/Methodology/Approach. Through screening the importance of indicators by the deep learning methods such as recurrent neural networks (RNNs), long short-term memory (LSTM), and gated recurrent unit (GRU), a selection model of topic popularity indicators based on AHP is set up. Findings. The results show that when topic popularity is being built quantitatively based on the DGI method and different weights of topic indicators are obtained from the help of AHP, the average accuracy of topic popularity prediction can reach 97.66%. The training speed is higher and the prediction precision is higher. Practical Implications. The method proposed in the paper can be used to calculate the popularity of each hot topic and generate the ranking list of topics’ popularities. Moreover, its future popularity can be predicted by deep learning methods. At the same time, a new application field of deep learning technology has been further discovered and verified. Originality/Value. This can lay a theoretical foundation for the formulation of topic popularity tendency prevention measures on the social network and provide an evaluation method which is consistent with the actual situation.

Quantifying shifts in topic popularity over 44 years of Austral Ecology

AbstractThe Ecological Society of Australia was founded in 1959, and the society’s journal was first published in 1976. To examine how research published in the society’s journal has changed over this time, we used text mining to quantify themes and trends in the body of work published by the Australian Journal of Ecology and Austral Ecology from 1976 to 2019. We used topic models to identify 30 ‘topics’ within 2778 full‐text articles in 246 issues of the journal, followed by mixed modelling to identify topics with above‐average or below‐average popularity in terms of the number of publications or citations that they contain. We found high inter‐decadal turnover in research topics, with an early emphasis on highly specific ecosystems or processes giving way to a modern emphasis on community, spatial and fire ecology, invasive species and statistical modelling. Despite an early focus on Australian research, papers discussing South American ecosystems are now among the fastest‐growing and most frequently cited topics in the journal. Topics that were growing fastest in publication rates were not always the same as those with high citation rates. Our results provide a systematic breakdown of the topics that Austral Ecology authors and editors have chosen to research, publish and cite through time, providing a valuable window into the historical and emerging foci of the journal.

Grey theory–based BP-NN co-training for dense sequence long-term tendency prediction

PurposeThe purpose of this paper is to solve the problems existing in topic popularity prediction in online social networks and advance a fine-grained and long-term prediction model for lack of sufficient data.Design/methodology/approachBased on GM(1,1) and neural networks, a co-training model for topic tendency prediction is proposed in this paper. The interpolation based on GM(1,1) is employed to generate fine-grained prediction values of topic popularity time series and two neural network models are considered to achieve convergence by transmitting training parameters via their loss functions.FindingsThe experiment results indicate that the integrated model can effectively predict dense sequence with higher performance than other algorithms, such as NN and RBF_LSSVM. Furthermore, the Markov chain state transition probability matrix model is used to improve the prediction results.Practical implicationsFine-grained and long-term topic popularity prediction, further improvement could be made by predicting any interpolation in the time interval of popularity data points.Originality/valueThe paper succeeds in constructing a co-training model with GM(1,1) and neural networks. Markov chain state transition probability matrix is deployed for further improvement of popularity tendency prediction.

The Research Trend of Employability in HE From 2000 to 2019--A Visual Analysis Using Citespace

Employability is about having the capability to gain initial employment, maintain employment and obtain new employment. Research on employability in each country is increasing because of the serious situation of graduate unemployment. There are lots of studies on employability from the range of its concept, key elements, to supports to raise the employability in higher education. Employability has been variously defined in terms of organization and policy. As long as the various studies about employability were published, it had been difficult to identify a big picture and directions for future research. CiteSpace, which is designed to analyze existing literature by co-citation networks, can provide a clear picture of the research in this field. This paper investigated and visualized the research trends of employability in higher education around the world. We constructed a framework for trends analyses based on theoretical reviews. All the data was collected on Scopus, one of the largest abstract and citation database of peer-reviewed literature. 661 articles published in international journals in past 2 decades were collected and analyzed. In terms of contributing countries, the major driving force is from the United Kingdom, and Australia. Yorke M, Harvey L and Tomlinson M are top cited authors. In terms of the popularity of research topics, recent employability research has mainly focused on university activities, class act, career planning, lunar side and international internship.

The Highs in Communication Research: Research Topics With High Supply, High Popularity, and High Prestige in High-Impact Journals

More and more scholarly attention is paid to dissecting discipline of communication research under the microscope thereby aiming at revealing foci of scientific interest. The lion’s share of research has hereby focused either on the supply side of research examining what topics scholars write about or at the popularity side of research shedding light on what scientific publications receive the most citations. Building up on this, we argue that these research strands are inadequate to the task of exhaustively identifying foci of scientific interest. Tailoring for the fragmented topical landscape of communication research, we propose an integrative combination of three metrics: supply, popularity, and prestige of research topics. By means of topic modeling, citation counts and citation networks, our study showcases how our approach is able to reveal the intellectual architecture of our discipline in order to identify relevant paths for further scientific inquiry.

Balancing of two-sided disassembly lines: Problem definition, MILP model and genetic algorithm approach

The recovery of end of life (EOL) products has become an important issue in terms of economic as well as social and environmental considerations. Recent rigid environmental regulations also contribute to the popularity of disassembly and product recovery topics among academicians and practitioners. Disassembly lines have been utilised to break EOL products into pieces and remove parts which can be reused in the manufacturing of new products. However, to the best of the authors’ knowledge, there is no research on the two-sided disassembly lines, which are used for disassembly of large-sized products. Therefore, this research contributes to literature by introducing the two-sided disassembly line balancing problem (TDLBP) and modelling it mathematically for the first time. The problem is depicted and the challenges are explored through extensive numerical examples. Secondly, a powerful genetic algorithm approach, called 2-GA, is developed for solving the introduced TDLBP considering complex AND/OR precedence relations. Computational tests are conducted to test the performance of the proposed 2-GA and the results are compared to those obtained from CPLEX and tabu search algorithm. From the comparison of the obtained solutions, it can be concluded that 2-GA has a superior performance in finding optimal (or at least near-optimal) solutions usually within less than one second.

Analysis of spatiotemporal characteristics of big data on social media sentiment with COVID-19 epidemic topics.

COVID-19 blocked Wuhan in China, which was sealed off on Chinese New Year's Eve. During this period, the research on the relevant topics of COVID-19 and emotional expressions published on social media can provide decision support for the management and control of large-scale public health events. The research assisted the analysis of microblog text topics with the help of the LDA model, and obtained 8 topics ("origin", "host", "organization", "quarantine measures", "role models", "education", "economic", "rumor") and 28 interactive topics. Obtain data through crawler tools, with the help of big data technology, social media topics and emotional change characteristics are analyzed from spatiotemporal perspectives. The results show that: (1) "Double peaks" feature appears in the epidemic topic search curve. Weibo on the topic of the epidemic gradually reduced after January 24. However, the proportion of epidemic topic searches has gradually increased, and a "double peaks" phenomenon appeared within a week; (2) The topic changes with time and the fluctuation of the topic discussion rate gradually weakens. The number of texts on different topics and interactive topics changes with time. At the same time, the discussion rate of epidemic topics gradually weakens; (3) The political and economic center is an area where social media is highly concerned. The areas formed by Beijing, Shanghai, Guangdong, Sichuan and Hubei have published more microblog texts. The spatial division of the number of Weibo social media texts has a high correlation with the economic zone division; (4) The existence of the topic of "rumor" will enable people to have more communication and discussion. The interactive topics of "rumors" always have higher topic popularity and low emotion text expressions. Through the analysis of media information, it helps relevant decision makers to grasp social media topics from spatiotemporal characteristics, so that relevant departments can accurately grasp the public's subjective ideas and emotional expressions, and provide decision support for macro-control response strategies and measures and risk communication.

Deciding what to observe: Thoughts for a post-WEIRD generation

Abstract The evolutionary social sciences (ESSs) are thriving, and seem to have entered a period of normal science. This is a good time to examine our own practices, theoretical and empirical, and to ask how we might improve. Here I review papers published in the past five years in EHB to explore major trends in the field. Theoretically, the popularity of certain topics (cooperation, mating, life history) has led to great progress, but might have narrowed our theoretical vision. Empirically, most research is still conducted in WEIRD populations, with a smaller mode of research in small-scale societies, and very little in the middle. I offer suggestions for broadening our theoretical and empirical scope, centered around the project of constructing a representative map of the human psychological and behavioral phenome.

Communication Rights for Social Bots?: Options for the Governance of Automated Computer-Generated Online Identities

AbstractSocial bots, automated agents operating in social networks, are suspected of influencing online debates, opinion-formation processes and thus, the outcome of elections and votes. They do so by contributing to the dissemination of illegal content and disinformation and by jeopardizing an accurate perception of the relevance and popularity of persons, topics, or positions, through their potentially unlimited communication and networking activities, all under the false pretense of human identity. This paper identifies and discusses preventive and repressive governance options for dealing with social bots on state, organizational, and individual levels respecting the constitutional provisions on free expression and opinion-formation.