Extracting a Topic Specific Dataset from a Twitter Archive

Abstract

Abstract. Datasets extracted from the microblogging service Twitter are often generated using specific query terms or hashtags. We describe how a dataset produced using the query term 'syria' can be increased in size to include tweets on the topic of Syria that do not contain that query term. We compare three methods for this task, using the top hashtags from the set as search terms, using a hand selected set of hashtags as search terms and using LDA topic modelling to cluster tweets and selecting appropriate clusters. We describe an evaluation method for accessing the relevance and accuracy of the tweets returned.

Smart Monitoring and Controlling of Government Policies Using Social Media and Cloud Computing

“…The sentiment analysis also served as an indicator for calculating threshold value, based upon which warning signals were generated for the government (See Section 4.4 Subsection (b)). The identification of theme was done by topic modeling (Llewellyn et al 2015). Network analysis (Walther and Kaisser 2013) helped in detection of prominent communities, engaged in GST discussion.…”

“…Content analysis deals with obtaining semantic content from the given text. This is achieved using techniques like sentiment analysis, topic modeling etc (Kassarjian 1977;Kayser and Blind 2017;Llewellyn et al 2015;Zhang et al 2016)…”

The Untold Story of USA Presidential Elections in 2016 - Insights from Twitter Analytics

“…An indicative list of methods for Twitter analytics is illustrated in the Table 1. [39] Hashtags analysis [8] @mentions Analysis [36] Word Cloud (most frequent words) [31] Reach metric [12] Sentiment Analysis [21] Polarity Analysis [35] E-motion Analysis [32] Topic Modelling [26] Lexical diversity [11] Network Analysis Space-Time Analysis Friend-follower Networks [13] Network layout [17] Network diameter [9] Centrality analysis [8] Cluster detection [42] Information flow networks [7] Time-trend analysis [27] Time series comparisons [4] Geo-spatial analysis [42] Geo-location analysis [38] Topic evolution [25] Descriptive analysis focuses on descriptive statistics, such as the number of tweets and its types, number of unique users, hashtags, @mention and hyperlinks added in the tweets with frequency, word cloud and the reach metrics. Word clouds help us to visualize the popular words / topics tweets [31].…”

“…Similarly, topic modelling identifies the key themes among the tweets through mining of unstructured text. [26]. Topic modelling was done in our study by using the tm and topicmodels libraries of R.…”

Avoiding the Drunkard's Search

“…For all other uses, contact the owner/author(s). sen by an expert panel as search queries; 2) collecting the random sample without specified search terms and extracting appropriate data [2]; 3) collecting from specific users that are known to be contributing to the debate [3].…”