Literature review on Real-time Location-Based Sentiment Analysis on Twitter

Sentiment analysis mainly supports sorting out the polarity and provides valuable information with the use of raw data in social media platforms. Many fields like health, business, and security require real-time data analysis for instant decision-making situations.Since Twitter is considered a popular social media platform to collect data easily, this paper is considering data analysis methods of Twitter data, real-time Twitter data analysis based on geo-location. Twitter data classification and analysis can be done with the use of diverse algorithms and deciding the most appropriate algorithm for data analysis, can be accomplished by implementing and testing these diverse algorithms.This paper is discussing the major description of sentiment analysis, data collection methods, data pre-processing, feature extraction, and sentiment analysis methods related to Twitter data. Real-time data analysis arises as a major method of analyzing the data available online and the real-time Twitter data analysis process is described throughout this paper. Several methods of classifying the polarized Twitter data are discussed within the paper while depicting a proposed method of Twitter data analyzing algorithm. Location-based Twitter data analysis is another crucial aspect of sentiment analyses, that enables data sorting according to geo-location, and this paper describes the way of analyzing Twitter data based on geo-location. Further, a comparison about several sentiment analysis algorithms used by previous researchers has been reported and finally, a conclusion has been provided.

Text Analysis Methods for Misinformation–Related Research on Finnish Language Twitter

The dissemination of disinformation and fabricated content on social media is growing. Yet little is known of what the functional Twitter data analysis methods are for languages (such as Finnish) that include word formation with endings and word stems together with derivation and compounding. Furthermore, there is a need to understand which themes linked with misinformation—and the concepts related to it—manifest in different countries and language areas in Twitter discourse. To address this issue, this study explores misinformation and its related concepts: disinformation, fake news, and propaganda in Finnish language tweets. We utilized (1) word cloud clustering, (2) topic modeling, and (3) word count analysis and clustering to detect and analyze misinformation-related concepts and themes connected to those concepts in Finnish language Twitter discussions. Our results are two-fold: (1) those concerning the functional data analysis methods and (2) those about the themes connected in discourse to the misinformation-related concepts. We noticed that each utilized method individually has critical limitations, especially all the automated analysis methods processing for the Finnish language, yet when combined they bring value to the analysis. Moreover, we discovered that politics, both internal and external, are prominent in the Twitter discussions in connection with misinformation and its related concepts of disinformation, fake news, and propaganda.

Review of Data Mining for Twitter Data Analysis

In today’s life Twitter, Facebook, Google are well known social sites that many uses for different purposes. Social sites are the fastest medium which delivers news to user as compared to the new paper and television. One among the online social networks like Twitter, has quickly gained fame as it provides people with the opportunity to communicate and share messages known as “tweets”. Tremendous value lies in automated analysis and data mining of such vast and diverse data to derive meaningful insights, which carries potential opportunities for businesses, consumers, product survey and political survey. In the proposed system of analysis of the tweets, a search query for topic is provided to extract required data using ‘clustering algorithm’ in machine learning. The unique advantage of using machine learning is that once an algorithm knows what to do with the information, it can do its job automatically. To deduce for a search query, the proposed system extracts feature from the tweets like keywords in tweets, number of words in tweets. The output tweet list can further be used for analysis for business improvement or for surveys.

Feeling the Void: Lack of Support for Isolation and Sleep Difficulties in Pregnant Women during the COVID-19 Pandemic Revealed by Twitter Data Analysis

Pregnant women face many physical and psychological changes during their pregnancy. It is known that stress, caused by many factors and life events such as the COVID-19 pandemic, can negatively impact the health of mothers and offspring. It is the first time social media, such as Twitter, are available and commonly used during a global pandemic; this allows access to a rich set of data. The objective of this study was to characterize the content of an international sample of tweets related to pregnancy and mental health during the first wave of COVID-19, from March to June 2020. Tweets were collected using GetOldTweets3. Sentiment analysis was performed using the VADER sentiment analysis tool, and a thematic analysis was performed. In total, 192 tweets were analyzed: 51 were from individuals, 37 from companies, 56 from non-profit organizations, and 48 from health professionals/researchers. Findings showed discrepancies between individual and non-individual tweets. Women expressed anxiety, depressive symptoms, sleeping problems, and distress related to isolation. Alarmingly, there was a discrepancy between distress expressed by women with isolation and sleep difficulties compared to support offered by non-individuals. Concrete efforts should be made to acknowledge these issues on Twitter while maintaining the current support offered.

TWITTER LOCATION-BASED DATA: EVALUATING THE METHODS OF DATA COLLECTION PROVIDED BY TWITTER API

Twitter data analysis is an emerging field of research that utilizes data collected from Twitter to address many issues such as disaster response, sentiment analysis, and demographic studies. The success of data analysis relies on collecting accurate and representative data of the studied group or phenomena to get the best results. Various twitter analysis applications rely on collecting the locations of the users sending the tweets, but this information is not always available. There are several attempts at estimating location based aspects of a tweet. However, there is a lack of attempts on investigating the data collection methods that are focused on location. In this paper, we investigate the two methods for obtaining location-based data provided by Twitter API, Twitter places and Geocode parameters. We studied these methods to determine their accuracy and their suitability for research. The study concludes that the places method is the more accurate, but it excludes a lot of the data, while the geocode method provides us with more data, but special attention needs to be paid to outliers.