Twitter Tweets Research Articles

A novel surveillance approach for disaster mental health.

BackgroundDisasters have substantial consequences for population mental health. Social media data present an opportunity for mental health surveillance after disasters to help identify areas of mental health needs. We aimed to 1) identify specific basic emotions from Twitter for the greater New York City area during Hurricane Sandy, which made landfall on October 29, 2012, and to 2) detect and map spatial temporal clusters representing excess risk of these emotions.MethodsWe applied an advanced sentiment analysis on 344,957 Twitter tweets in the study area over eleven days, from October 22 to November 1, 2012, to extract basic emotions, a space-time scan statistic (SaTScan) and a geographic information system (QGIS) to detect and map excess risk of these emotions.ResultsSadness and disgust were among the most prominent emotions identified. Furthermore, we noted 24 spatial clusters of excess risk of basic emotions over time: Four for anger, one for confusion, three for disgust, five for fear, five for sadness, and six for surprise. Of these, anger, confusion, disgust and fear clusters appeared pre disaster, a cluster of surprise was found peri disaster, and a cluster of sadness emerged post disaster.ConclusionsWe proposed a novel syndromic surveillance approach for mental health based on social media data that may support conventional approaches by providing useful additional information in the context of disaster. We showed that excess risk of multiple basic emotions could be mapped in space and time as a step towards anticipating acute stress in the population and identifying community mental health need rapidly and efficiently in the aftermath of disaster. More studies are needed to better control for bias, identify associations with reliable and valid instruments measuring mental health, and to explore computational methods for continued model-fitting, causal relationships, and ongoing evaluation. Our study may be a starting point also for more fully elaborated models that can either prospectively detect mental health risk using real-time social media data or detect excess risk of emotional reactions in areas that lack efficient infrastructure during and after disasters. As such, social media data may be used for mental health surveillance after large scale disasters to help identify areas of mental health needs and to guide us in our knowledge where we may most effectively intervene to reduce the mental health consequences of disasters.

IMPLEMENTATION OF EVENT EXTRACTION FROM TWITTER USING LDA

It is a simple approach for extracting events from twitter (tweets).Examples of events are national conferences, competitive exams, jobs opening, meditation camps etc. Tweets are the up-to-date and comprehensive collection of information about the current topic. It identifies the specific events in unstructured or semi-structured tweets. It transforms unstructured information in a collection of tweets into a structured database or in the form of retrieval calendar entries that contains information about specific event, time and location. The main goal of this paper is to explore different approaches for extracting the events. This paper focuses on usefulness of accurately extracting Major events.

Polarized words: discourse on the boycott of Israel, social justice and conflict resolution

PurposeThe study aimed to investigate how Israelis and Palestinians, Jews and others from around the world present their views on boycott, divestment and sanctions (BDS) and the Palestinian Academic and Cultural Boycott of Israel (PACBI). The quality of discourse was examined along with the implications of the rhetoric for social-justice and conflict resolution frameworks.Design/methodology/approachThis qualitative study analyzed 257 texts (newspaper articles, opinion pieces, YouTube videos, emails. Facebook posts, Twitter tweets, campaigns and websites) for content and quality of discourse and for their implications for social-justice and conflict resolution work.FindingsMost texts divided into those in favor of the boycott and those opposed. The content was also polarized − most pro-BDS texts saw Israel as a settler-colonial enterprise, and emphasized issues of social-justice, whereas opponents perceived Israel as a legitimate nation and were skeptical of the human rights angle. The main types of discourse discerned included: ethnocentric talk, attack and intellectual discussion, regardless of national/ethnic origin of the writer or stance toward the boycott.Research limitations/implicationsDifferent types of texts were analyzed, which did not always fit easily into the discourse categories. Because this was the first study of its kind and looked at limited years, results should be approached with this in mind.Practical implicationsThe rhetoric leaves little place for dialogue between those in favor and those opposed. Specific suggestions for combining social-justice work and conflict resolution work are offered.Social implicationsBDS discourse in its present form hampers finding a solution to the conflict and abuse of Palestinian rights. A new approach is needed to try to resolve these issues.Originality/valueBecause there are few systematic studies on BDS, this article provides insight into how people discuss the strategy and how it connects to frameworks for resolving conflicts.

Predicting Movie Genre Preferences from Personality and Values of Social Media Users

We propose a novel technique to predict a user’s movie genre preference from her psycholinguistic attributes obtained from user social media interactions. In particular, we build machine learning based classification models that take user tweets as input to derive her psychological attributes: personality and value scores, and gives her movie genre preference as output. We train these models using user tweets in Twitter, and her reviews and ratings of movies of different genres in Internet movie database (IMDb). We exploit a key concept of psychology, i.e., an individual’s personality and values may influence her choice in performing different actions in real life. We have investigated how personality and values independently and collectively influence a user preference on different movie genres. Our proposed model can be used for recommending movies to social media users.

How journalists engage in branding on Twitter: individual, organizational, and institutional levels

ABSTRACTIn a social media age, branding is an increasingly visible aspect of identity construction online. For media professionals generally and journalists especially, branding on spaces such as Twitter reveals the complicated set of forces confronting such public-facing actors as they navigate tensions between personal disclosure for authenticity and professional decorum for credibility, and between establishing one’s own distinctiveness and promoting one’s employer or other stakeholders. While studies have begun to reveal what journalists say about branding, they have yet to provide a broad profile of what they do. This study takes up that challenge through a content analysis of the Twitter profiles and tweets of a representative sample of 384 U.S. journalists. We focus on the extent of branding practices; the levels at which such branding occurs, whether to promote one’s self (individual), one’s news organization (organizational), or the journalism profession at large (institutional); and how other social media practices may be related to forms of journalistic branding. Results suggest that branding is now widely common among journalists on Twitter; that branding occurs at all three levels but primarily at the individual and organizational levels, with organizational branding taking priority; and that time on Twitter is connected with more personal information being shared.

Multilingual author profiling on Facebook

Author profiling is the identification of demographic features of an author by examining his written text. Recently, it has attracted the attention of research community due to it’s potential applications in forensic, security, marketing, fake profiles identification on online social networking sites, capturing sender of harassing messages etc. We need benchmark corpora to develop and evaluate techniques for author profiling. Majority of the existing corpora are for English and other European languages but not for under–resourced South Asian languages, like Roman Urdu (written using English alphabets). Roman Urdu is used in daily communication by a large number of native speakers of Urdu around the world particularly in Facebook posts/comments, Twitter tweets, blogs, chat blogs and SMS messaging. The construction of sentences of Urdu while using alphabets of English transforms the language properties of the text. We aim to investigate the behavior of existing author profiling techniques for multilingual text consisting of English and Roman Urdu, concretely for gender and age identification. We here focus on author profiling on Facebook by (i) developing a multilingual (Roman Urdu and English) corpus, (ii) manually building of a bilingual dictionary for translating Roman Urdu words into English, (iii) modeling existing state-of-the-art author profiling techniques by using content based features (word and character N–grams) and 64 different stylistic based features (11 lexical word based features, 47 lexical character based features and 6 vocabulary richness measures) for age and gender identification on multilingual and translated corpora, (iv) evaluating and comparing the behavior of above mentioned techniques on multilingual and translated corpora. Our extensive empirical evaluation shows that (i) existing author profiling techniques can be used for multilingual text (Roman Urdu + English) as well as monolingual text (corpus obtained after translating multilingual corpus using bilingual dictionary), (ii) content based methods outperform stylistic based methods for both gender and age identification task and (iii) translation of multilingual corpus to monolingual text does not improve results.

A model for sentiment and emotion analysis of unstructured social media text

Sentiment analysis has applications in diverse contexts such as in the gathering and analysis of opinions of individuals about various products, issues, social, and political events. Understanding public opinion can help improve decision making. Opinion mining is a way of retrieving information via search engines, blogs, microblogs and social networks. Individual opinions are unique to each person, and Twitter tweets are an invaluable source of this type of data. However, the huge volume and unstructured nature of text/opinion data pose a challenge to analyzing the data efficiently. Accordingly, proficient algorithms/computational strategies are required for mining and condensing tweets as well as finding sentiment bearing words. Most existing computational methods/models/algorithms in the literature for identifying sentiments from such unstructured data rely on machine learning techniques with the bag-of-word approach as their basis. In this work, we use both unsupervised and supervised approaches on various datasets. Unsupervised approach is being used for the automatic identification of sentiment for tweets acquired from Twitter public domain. Different machine learning algorithms such as Multinomial Naive Bayes (MNB), Maximum Entropy and Support Vector Machines are applied for sentiment identification of tweets as well as to examine the effectiveness of various feature combinations. In our experiment on tweets, we achieve an accuracy of 80.68% using the proposed unsupervised approach, in comparison to the lexicon based approach (the latter gives an accuracy of 75.20%). In our experiments, the supervised approach where we combine unigram, bigram and Part-of-Speech as feature is efficient in finding emotion and sentiment of unstructured data. For short message services, using the unigram feature with MNB classifier allows us to achieve an accuracy of 67%.

An adaptive hawkes process formulation for estimating time-of-day zonal trip arrivals with location-based social networking check-in data

Location-Based Social Networking (LBSN) services, such as Foursquare, Facebook check-ins, and Geo-tagged Twitter tweets, have emerged as new secondary data sources for studying individual travel mobility patterns at a fine-grained level. However, the differences between human social behavioral and travel patterns can cause significant sampling bias for travel demand estimation. This paper presents a dynamic model to estimate time-of-day zonal trip arrival patterns. In the proposed model, the state propagation is formulated by the Hawkes process; the observation model implements LBSN sampling. The proposed model is applied to Foursquare check-in data collected from Austin, Texas in 2010 and calibrated with Origin-Destination (OD) data and time of day factor from Capital Area Metropolitan Planning Organization (CAMPO). The proposed model is compared with a simple aggregation model of trip purposes and time of day based on a prior daily OD estimation model using the LBSN data. The results illustrate the promising benefits of applying stochastic point process models and state-space modeling in time-of-day zonal arrival pattern estimation with the LBSN data. The proposed model can significantly reduce the number of parameters to calibrate in order to reduce the sampling bias of LBSN data for trip arrival estimation.

An unsupervised multilingual approach for online social media topic identification

Social media data can be valuable in many ways. However, the vast amount of content shared and the linguistic variants of languages used on social media are making it very challenging for high-value topics to be identified. In this paper, we present an unsupervised multilingual approach for identifying highly relevant terms and topics from the mass of social media data. This approach combines term ranking, localised language analysis, unsupervised topic clustering and multilingual sentiment analysis to extract prominent topics through analysis of Twitter's tweets from a period of time. It is observed that each of the ranking methods tested has their strengths and weaknesses, and that our proposed ‘Joint’ ranking method is able to take advantage of the strengths of the ranking methods. This ‘Joint’ ranking method coupled with an unsupervised topic clustering model is shown to have the potential to discover topics of interest or concern to a local community. Practically, being able to do so may help decision makers to gauge the true opinions or concerns on the ground. Theoretically, the research is significant as it shows how an unsupervised online topic identification approach can be designed without much manual annotation effort, which may have great implications for future development of expert and intelligent systems.

A Lexicon-based Approach to Build Service Provider Reputation from Arabic Tweets in Twitter

Nowadays Social media has become a popular com-munication tool among Internet users. Many users share opinions and experiences on different service providers everyday through the social media platforms. Thus, these platforms become valuable sources of data which can be exploited and used efficiently to support decision-making. However, finding and monitoring customers’ opinions on the social media is difficult task due to the fast growth of the content. This work focus on using Twitter for the task of building service providers’ reputation. Particularly, service provider’s reputation is calculated from the collected Saudi tweets in Twitter. To do so, a Saudi dialect lexicon has been developed as a basic component for sentiment polarity to classify words extracted from Twitter into either a positive or negative word. Then, beta probability density functions have been used to combine feedback from the lexicon to derive reputation scores. Experimental evaluations show that the proposed approach were consistent with the results of Qaym, a website that calculates restaurants’ rankings based on consumer ratings and comments.

A Credibility Analysis System for Assessing Information on Twitter

Information credibility on Twitter has been a topic of interest among researchers in the fields of both computer and social sciences, primarily because of the recent growth of this platform as a tool for information dissemination. Twitter has made it increasingly possible to offer near-real-time transfer of information in a very cost-effective manner. It is now being used as a source of news among a wide array of users around the globe. The beauty of this platform is that it delivers timely content in a tailored manner that makes it possible for users to obtain news regarding their topics of interest. Consequently, the development of techniques that can verify information obtained from Twitter has become a challenging and necessary task. In this paper, we propose a new credibility analysis system for assessing information credibility on Twitter to prevent the proliferation of fake or malicious information. The proposed system consists of four integrated components: a reputation-based component, a credibility classifier engine, a user experience component, and a feature-ranking algorithm. The components operate together in an algorithmic form to analyze and assess the credibility of Twitter tweets and users. We tested the performance of our system on two different datasets from 489,330 unique Twitter accounts. We applied 10-fold cross-validation over four machine learning algorithms. The results reveal that a significant balance between recall and precision was achieved for the tested dataset.

Fear on the networks: analyzing the 2014 Ebola outbreak.

ABSTRACTDuring the 2014 Ebola outbreak, information spread via multiple platforms, including social networks and Internet search engines. This report analyzes Twitter tweets, Facebook posts, and Google trends, as well as several other Internet resources, from March – November 2014. Understanding the types of discussions, social behaviors, feelings expressed, and information shared during the Ebola outbreak can help health organizations improve communication interventions and avert misinformation and panic during health emergencies.In all, 6 422 170 tweets, 83 Facebook posts, and Google search trends were integrated with 63 chronological Ebola-related events. Events that prompted a surge in tweets using #ebola were related to new cases of infection or the entry of the disease into a new goegraphic area. Most tweets were re-tweets of information provided by news agencies and official health organizations. Events related to new infections and deaths seemed to correlate with an increase of words that express fear. Google results concurred with Twitter and Facebook.Data from social media activity can be used to form hypotheses about how the public responds to and behaves during public health events, prompting health organizations to adopt new strategies for communications interventions. Furthermore, a spike in activity around a topic can be used as a surveillance technique to signal to health authorities that an outbreak may be underway. It is also recommended that news agencies, which engage with the public most often, consider content review by health experts as part of their health communications process.

Twitter Streaming and Analysis through R

Objectives: To retrieve tweets from Twitter through Twitter API. The domain chosen for analysis is Make-In-India Dataset. Methods/Statistical Analysis: This paper consists of two phases of work: 1. Data Streaming from Twitter, 2. Knowledge Mining through R-Studio. Methods used for the two key operations are: 1. Twitter API and 2. Sentiment Analysis through R. Twitter application is created to request for connection with the Twitter database. Once connection establishes, authentication keys are generated. Providing the search key “Make-In-India” and number of keys required, a file with .df (data frame) is generated with the tweets and is converted into .CSV (Comma Separated Values) file which is suitable Analysis. Sentiment Analysis1 is also called Opinion mining talks about retrieving facts from the tweets such as how many people supporting Make-In-India (or) how many are negative with the scheme (or) how many are neutral with it. For this process, a negative words file and a positive words file is taken for comparison with the tweet data to calculate positive score and negative score of the tweet. The difference of these scores gives us with the final score of the tweet. Findings: The number of tweets identified as positive (or) negative (or) neutral so that the status of Make-In-India can be visualised in a graph. Firstly, the extraction of Tweets is from Twitter through R-Studio Environment About “Make-In-India”. Secondly, we parse the extracted raw tweets using R according to the types and store in .CSV format in R database. Scores are calculated for all the tweets and stored in a file. In the third, we perform visual analysis from the stored data using R statistical software to conclude the impact of the program. Application/Improvements: Application of the methodology is to get findings2 from the public opinions which are available from Twitter tweets on a particular government issue, political parties and medical status around the country. Also it is useful to assess the popularity of the political leader and the program. Decision making is possible through sentiment analysis of user tweets.

Presidential Candidates" Twitter Use and the Linkage Pattern of Twitter users in the 2012 Presidential Election

The study aimed to examine how the five presidential candidates - Barack Obama, Mitt Romney, Rick Santorum, Newt Gingrich, and Ron Paul - used Twitter in their 2012 presidential election campaigns and how Twitter received information from the candidates and shared information with other Twitter users. Among 30 million Twitter who followed these five candidates, most individuals followed either Obama or one or multiple Republican candidates, but rarely followed across the party line. To find which model explains Twitter users following patterns better, the author examined the two-step flow model and the network model. Based on analysis of randomly selected 180 Twitter who followed any of the five candidates, this study found that their Twitter activities fitted the network model, in which shared information with each other beyond directly getting tweets from their favored candidate. In this network model, some of the seemed to emerge as opinion leaders by issuing plenty of tweets and having more followers than those they follow, also known as one-way friends. The author also downloaded the Twitter profile pages of the five candidates and all their tweets from when they set up their Twitter account through March 2012. To content analyze the tweets of the candidates, the author randomly selected 500 tweets from the five candidates, 100 from each candidate, and analyzed them to find emerging 11 categories, which covered mentioning of their performance and ideas, criticism of their opponents, solicitation, thanks to voters, personal-side stories, and event reminders. The five candidates heavily used Twitter as a hook to hashtags and http links that would provide more detailed information for followers. They still used Twitter mostly as a textual communication tool, but they slowly made a move to visuals. In terms of message content, Republican candidates heavily cited others, for example, the mass media, to describe their ideas and performance and to criticize their opponents. But Obama didnt seem to rely on external sources for the same purposes. This study used all 30 million Twitter to find which candidate they followed. But it used a small size of Twitter and tweets for other analyses. Future studies are suggested to analyze larger samples for more accurate results.

A hybrid approach to decision making and information fusion: Combining humans and artificial agents

This paper argues that hybrid human–agent systems can support powerful solutions to relevant problems such as Environmental Crisis management. However, it shows that such solutions require comprehensive approaches covering different aspects of data processing, model construction and the usage. In particular, the solutions (i) must be able to cope with complex correlations (as different data sources are used) and processing of large amounts of data, (ii) must be robust against modeling imperfections and (iii) human–machine interaction (HMI) approaches must facilitate human use of crisis management tools and reduce the likelihood of miscommunication.In this paper the relevant problem is an environmental protection application involving the detection and tracking of gases in case of chemical spills in an urban area. We show that a combination of Bayesian Networks, agent paradigm and systematic approaches to implementing HMI, support effective and robust solutions. To better integrate human information and demonstrate the usefulness of user generated crisis response information we developed a social media harvesting interface based on data from Twitter tweets and a visual interface to facilitate human smell classification.

TopicSketch: Real-Time Bursty Topic Detection from Twitter

Twitter has become one of the largest microblogging platforms for users around the world to share anything happening around them with friends and beyond. A bursty topic in Twitter is one that triggers a surge of relevant tweets within a short period of time, which often reflects important events of mass interest. How to leverage Twitter for early detection of bursty topics has therefore become an important research problem with immense practical value. Despite the wealth of research work on topic modelling and analysis in Twitter, it remains a challenge to detect bursty topics in real-time. As existing methods can hardly scale to handle the task with the tweet stream in real-time, we propose in this paper $\sf {TopicSketch}$ , a sketch-based topic model together with a set of techniques to achieve real-time detection. We evaluate our solution on a tweet stream with over 30 million tweets. Our experiment results show both efficiency and effectiveness of our approach. Especially it is also demonstrated that $\sf {TopicSketch}$ on a single machine can potentially handle hundreds of millions tweets per day, which is on the same scale of the total number of daily tweets in Twitter, and present bursty events in finer-granularity.

Two Studies on Twitter Networks and Tweet Content in Relation to Amyotrophic Lateral Sclerosis (ALS): Conversation, Information, and 'Diary of a Daily Life'.

To date, there is no research examining how adults with Amyotrophic Lateral Sclerosis (ALS) or Motor Neurone Disease (MND) and severe communication disability use Twitter, nor the use of Twitter in relation to ALS/MND beyond its use for fundraising and raising awareness. In this paper we (a) outline a rationale for the use of Twitter as a method of communication and information exchange for adults with ALS/MND, (b) detail multiple qualitative and quantitative methods used to analyse Twitter networks and tweet content in the our studies, and (c) present the results of two studies designed to provide insights on the use of Twitter by an adult with ALS/MND and by #ALS and #MND hashtag communities in Twitter. We will also discuss findings across the studies, implications for health service providers in Twitter, and directions for future Twitter research in relation to ALS/MND.

Citizen-Centric Urban Planning through Extracting Emotion Information from Twitter in an Interdisciplinary Space-Time-Linguistics Algorithm

Traditional urban planning processes typically happen in offices and behind desks. Modern types of civic participation can enhance those processes by acquiring citizens’ ideas and feedback in participatory sensing approaches like “People as Sensors”. As such, citizen-centric planning can be achieved by analysing Volunteered Geographic Information (VGI) data such as Twitter tweets and posts from other social media channels. These user-generated data comprise several information dimensions, such as spatial and temporal information, and textual content. However, in previous research, these dimensions were generally examined separately in single-disciplinary approaches, which does not allow for holistic conclusions in urban planning. This paper introduces TwEmLab, an interdisciplinary approach towards extracting citizens’ emotions in different locations within a city. More concretely, we analyse tweets in three dimensions (space, time, and linguistics), based on similarities between each pair of tweets as defined by a specific set of functional relationships in each dimension. We use a graph-based semi-supervised learning algorithm to classify the data into discrete emotions (happiness, sadness, fear, anger/disgust, none). Our proposed solution allows tweets to be classified into emotion classes in a multi-parametric approach. Additionally, we created a manually annotated gold standard that can be used to evaluate TwEmLab’s performance. Our experimental results show that we are able to identify tweets carrying emotions and that our approach bears extensive potential to reveal new insights into citizens’ perceptions of the city.

Arabic Rumours Identification By Measuring The Credibility Of Arabic Tweet Content

Twitter enjoys the fame of the most popular and widely used as a platform for socializing, including all aspects of life current affairs, religious ideas, political issues, scientific research, and general knowledge. Every single activity of day to day life and human behavior and values is lodged at this platform. Sending and receiving messages on Twitter (tweets) with is limited to 140 characters, In this research the author attempts to understand the characteristics of those Arabic rumour (falsified information stream) patterns. False tweets could be a rumour which is mostly recognized as a representative whose legitimacy, authenticity, precision and significance is either unverifiable or unreliable. Arabic rumours may propagate misinformation on social networks. In this research, the author illustrates the difficulty of Arabic rumour identification in twitter social platform by studying the impact based on Arabic tweet content. Furthermore, the author explains how these content features are too influential in measuring the credibility of those Arabic tweets.

Scholarly Sharing via Twitter: #icanhazpdf Requests for Health Sciences Literature

<p><strong>Introduction:</strong><span> Although requesting access to journal articles and books via colleagues and authors is a long-established academic practice, websites and social media platforms have broadened the scope and visibility of academic literature sharing among researchers. On Twitter, the #icanhazpdf hashtag has emerged as a way for researchers to request and obtain journal articles quickly and efficiently. This study analyzes use of the #icanhazpdf hashtag as a means of obtaining health sciences literature. </span><strong>Methods:</strong><span> RowFeeder software was used to monitor and aggregate #icanhazpdf requests between 1 February and 30 April 2015. This software records data such as Twitter handle, tweet content, tweeter location, date, and time. Tweets were hand-coded for the journal subject area, the requestor’s geographic location, and the requestor’s occupational sector. </span><strong>Results:</strong><span> There were 302 requests for health sciences literature during the study period. Many requests were made by users affiliated with a post-secondary academic institution (45%, </span><em>n</em><span> = 136). Very few requests were made by users located in Canada (</span><em>n</em><span> = 15). </span><strong>Conclusion:</strong><span> #icanhazpdf requests for health sciences literature account for a relatively small proportion of peer-to-peer article sharing activities when compared with other online platforms. Nevertheless, this study provides evidence that some faculty and students are choosing social media over the library as a means of obtaining health sciences literature. Examining peer-to-peer article sharing practices can provide insights into patron behaviour and expectations.</span></p>