Emotion evolutions of sub-topics about popular events on microblogs

Abstract

Purpose The development of social media has led to large numbers of internet users now producing massive amounts of user-generated content (UGC). UGC, which shows users’ opinions about events directly, is valuable for monitoring public opinion. Current researches have focused on analysing topic evolutions in UGC. However, few researches pay attention to emotion evolutions of sub-topics about popular events. Important details about users’ opinions might be missed, as users’ emotions are ignored. This paper aims to extract sub-topics about a popular event from UGC and investigate the emotion evolutions of each sub-topic. Design/methodology/approach This paper first collects UGC about a popular event as experimental data and conducts subjectivity classification on the data to get subjective corpus. Second, the subjective corpus is classified into different emotion categories using supervised emotion classification. Meanwhile, a topic model is used to extract sub-topics about the event from the subjective corpora. Finally, the authors use the results of emotion classification and sub-topic extraction to analyze emotion evolutions over time. Findings Experimental results show that specific primary emotions exist in each sub-topic and undergo evolutions differently. Moreover, the authors find that performance of emotion classifier is optimal with term frequency and relevance frequency as the feature-weighting method. Originality/value To the best of the authors’ knowledge, this is the first research to mine emotion evolutions of sub-topics about an event with UGC. It mines users’ opinions about sub-topics of event, which may offer more details that are useful for analysing users’ emotions in preparation for decision-making.

Tracking and Analyzing Public Emotion Evolutions During COVID-19: A Case Study from the Event-Driven Perspective on Microblogs

“…Previous research on sentiment analysis in social networks has generated fruitful results using supervised classifier learning [ 19 , 20 , 21 , 22 ] and unsupervised emotion lexicon-based methods [ 23 , 24 ]. Most supervised methods are conducted by extracting linguistic features and constructing classifiers using machine-learning or deep-learning techniques.…”

“…Reference [ 31 ] found that during the 2007 Virginia Tech shooting, anger was the most frequently expressed emotion on Twitter, followed by fright, sadness, and anxiety. In terms of natural disasters, Reference [ 21 ] collected microblogs about the “H7N9” influenza and classified them into different emotion categories using a supervised classification method. A topic model was then used to extract subtopics about the event.…”

Emotion-Aware Event Summarization in Microblogs

“…Several works have tried to model both topics and emotion. [36] extracts topics using LDA [2], and the emotion of each microblog is determined using a supervised emotion classifier. The topic-emotion models in [9,16,26,27,35] learn a supervised topicaware emotion classifier.…”

Is hybrid AI suited for hybrid threats? Insights from social media analysis

“…This disjoint analysis is a limitation of those approaches as meaningful clues hidden in online data are often a combination of topics and subjective aspects and their identification involves analysis of emotions conveyed towards specific topics. To overcome this limitation, several studies addressed the dynamics of emotions or opinions in time [29] as well as detecting the mapping between the emotional categories and linguistic instances [30].…”