Search results

The novel Coronavirus (COVID-19) pandemic, which started in late December 2019, has spread to more than 200 countries. As no vaccine is yet available for this pandemic, government and health agencies are taking draconian steps to contain it. This pandemic is also trending on social media, particularly on Twitter. The purpose of this study is to explore and analyze the general public reactions to the COVID-19 outbreak on Twitter.

This study conducts a thematic analysis of COVID-19 tweets through VOSviewer to examine people’s reactions related to the COVID-19 outbreak in the world. Moreover, sequential pattern mining (SPM) techniques are used to find frequent words/patterns and their relationship in tweets.

Seven clusters (themes) were found through VOSviewer: Cluster 1 (green): public sentiments about COVID-19 in the USA. Cluster 2 (red): public sentiments about COVID-19 in Italy and Iran and a vaccine, Cluster 3 (purple): public sentiments about doomsday and science credibility. Cluster 4 (blue): public sentiments about COVID-19 in India. Cluster 5 (yellow): public sentiments about COVID-19’s emergence. Cluster 6 (light blue): public sentiments about COVID-19 in the Philippines. Cluster 7 (orange): Public sentiments about COVID-19 US Intelligence Report. The most frequent words/patterns discovered with SPM were “COVID-19,” “Coronavirus,” “Chinese virus” and the most frequent and high confidence sequential rules were related to “Coronavirus, testing, lockdown, China and Wuhan.”

The methodology can be used to analyze the opinions/thoughts of the general public on Twitter and to categorize them accordingly. Moreover, the categories (generated by VOSviewer) can be correlated with the results obtained with pattern mining techniques.

This study has a significant socio-economic impact as Twitter offers content posting and sharing to billions of users worldwide.

According to the authors’ best knowledge, this may be the first study to carry out a thematic analysis of COVID-19 tweets at a glance and mining the tweets with SPM to investigate how people reacted to the COVID-19 outbreak on Twitter.

The existing traditional recommendations based on content-based filtering (CBF), collaborative filtering (CF) and hybrid approaches are inadequate for recommending practice challenges in programming online judge (POJ). These systems only consider the preferences of the target users or similar users to recommend items. In the learning environment, recommender systems should consider the learning path, knowledge level and ability of the learner. Another major problem in POJ is the learners don't give ratings to practice challenges like e-commerce and video streaming portals. This purpose of the proposed approach is to overcome the abovementioned shortcomings.

To achieve the context-aware practice challenge recommendation, the data preparation techniques including implicit rating extraction, data preprocessing to remove outliers, sequence-based learner clustering and utility sequence pattern mining approaches are used in the proposed approach. The approach ensures that the recommender system considers the knowledge level, learning path and learning goals of the learner to recommend practice challenges.

Experiments on practice challenge recommendations conducted using real-world POJ dataset show that the proposed system outperforms other traditional approaches. The experiment also demonstrates that the proposed system is recommending challenges based on the learner's current context. The implicit rating extracted using the proposed approach works accurately in the recommender system.

The proposed system contains the following novel approaches to address the lack of rating and context-aware recommendations. The mathematical model was used to extract ratings from learner submissions. The statistical approach was used in data preprocessing. The sequence similarity-based learner clustering was used in transition matrix. Utilizing the rating as a utility in the USPAN algorithm provides useful insights into learner–challenge relationships.

This study aims to overcome the problem of traditional association rules relying almost entirely on expert experience to set relevant interest indexes in mining. Second, this project can effectively solve the problem of four types of rules being present in the database at the same time. The traditional association algorithm can only mine one or two types of rules and cannot fully explore the database knowledge in the decision-making process for library recommendation.

The authors proposed a Markov logic network method to reconstruct association rule-mining tasks for library recommendation and compared the method proposed in this paper to traditional Apriori, FP-Growth, Inverse, Sporadic and UserBasedCF algorithms on two history library data sets and the Chess and Accident data sets.

The method used in this project had two major advantages. First, the authors were able to mine four types of rules in an integrated manner without having to set interest measures. In addition, because it represents the relevance of mining in the network, decision-makers can use network visualization tools to fully understand the results of mining in library recommendation and data sets from other fields.

The time cost of the project is still high for large data sets. The authors will solve this problem by mapping books, items, or attributes to higher granularity to reduce the computational complexity in the future.

The authors believed that knowledge of complex real-world problems can be well captured from a network perspective. This study can help researchers to avoid setting interest metrics and to comprehensively extract frequent, rare, positive, and negative rules in an integrated manner.