Limited Offer Get 25% off — use code BESTW25
No AI No Plagiarism On-Time Delivery Free Revisions
Claim Now
Prices start at $5 per page · plagiarism-free papers · free revisions for 14 days 24/7 support: support@bestwriters.com
Uncategorized

Twitter is an easy to use source of data

  • Posted
  • Authoradmin
  • Length4,632 words
  • Reading time21 min
Write My Assignment FREE

On Whether Tweets Predict Elections

A review of the literature indicates “No”

Damien Bourke

School of Information Technology & Mathematical Sciences

University of South Australia

Mawson Lakes, Australia

bouda004@mymail.unisa.edu.au

Abstract—Twitter is an easy to use source of data, and several researchers have used the data contained within tweets to make election predictions. However, Twitter users are not a representative sample of the general population, and thus using tweets as a source for predictions should be undertaken with caution, if used at all. Although certain models produced thus far claim to predict election results, a closer examination finds that they lack methodological rigor, thus casting their results in doubt. Improvements in existing models may lead to better results, and ideas for future, more robust models are discussed. However, Twitter should, at most, complement rather than replace existing forecasting methods.

Keywords—twitter; election results; prediction

  1. Introduction

Twitter (www.twitter.com) is a microblogging platform whereby users publish tweets, which are visible to users’ followers. A tweet has a 140-character limitation; and thus, conveys less information than either a Facebook post or blog entry (since neither face the same 140-character restraint). Although figures have not been updated since August 2013, Twitter users have been estimated to send approximately 500 million tweets per day [1]. There are approximately 313 million [2] falling into three categories.

The first type of users is individuals representing themselves, which is the most common type of account. However, it must be noted that accounts can be shared between users and/or devices. For example, after Donald Trump was nominated as the Republican presidential candidate, his official account, @realDonaldTrump, had posts sent from at least two devices: at least one Android mobile telephone and at least one iPhone. As the attitude and content of the messages from either device varied, it is suspected that the Android messages were sent by Donald Trump himself, while the iPhone messages were sent by his campaign staff (the iPhone-based messages were notable more restrained compared to the more puerile Android-based messages) [3].

The second type of users is individuals who represent organizations. For example, posts made on behalf of corporations or political parties are done so by one or more (unknown and potentially unknowable) individuals representing that corporation or party. For example, it is unclear as to who is the author of tweets from @secularparty; similarly, it is unclear how many individuals post on behalf of this account for the Secular Party of Australia.

The third type of users is automated (botnet) accounts. For example, @RealPressSecBot, which “Checks for new @realDonalTrump tweets every 5 min & transforms them into correct Presidential statement format.” [4]. One estimate of the total number of botnet accounts is in the millions [5], although it the actual number of such accounts is unknown.

  1. Source of Twitter Data

With regards to the time during which election campaigns took place, a review of 127 studies [6] found three main sources of data were obtained from Twitter: from candidates or parties, from the general public, and from mediated events.

Tweets from political parties or candidates fell into two basic categories: broadcasting messages, and replies to messages. Previous research found that most tweets from politicians or political parties adopted a broadcast style; these tweets were intended for one-way dissemination of content from the sender to the receiver. Such tweets include retweets, and represent posting about a topic, rather responding to a topic. Thus, these types of tweets focused on self-promotion [7], impression management [8], information dissemination [9], and party mobilization [10]. By way of example, a self-promotional tweet is shown in Fig. 1, where the tween from an organization user is directed to both @ScottMorrisonMP and the Twitter feeds based on hashtags #qt (Question time in the Australian Federal Parliament) and #auspol (Australian politics).

This Govt has a plan to drive the economy forward and get expenditure under control – @ScottMorrisonMP #qt #auspol

Fig. 1 Tweet from Liberal Party of Australia (@LiberalAus), 13-Sep-2016

However, more recent research indicates that usage of Twitter has moved toward a more conversation and dyadic style of interaction; an increasing percentage of tweets contain replies and mentions [11] (both of which use the “@” feature to direct tweets to the specified users), as shown in Fig. 2, where the tweet from an organization is directing to two individuals, @PaulineHansonOZ and @LyleShelton, while at the same time the post is observable to all followers of @aussexparty, as well as being available in the Twitter feed for #auspol (Australian politics).

Absolute silence from @PaulineHansonOz and @LyleShelton on the Christian extremists who vandalised a war memorial in Queensland. #auspol

Fig. 2 Tweet from Australian Sex Party (@aussexparty), 03-Mar-2017

Tweets from the general public also fell into two basic categories: messages to parties or candidates, and messages about parties or candidates. Messages to parties or candidates involve mentioning the user account by prefixing their account with “@”, as shown in Fig. 3, where the tweet from an individual user is directed to @NSWLabor and is available in the Twitter feed for #abortion.

Dear @NSWLabor I feel betrayed as a woman that the party has male MPs in it who denied my bodily autonomy today. Voting Green. #abortion

Fig. 3 Tweet from Jackie McMillan (@MissDissentEats) mentioning Australian Labor Party, 11-May-2017

Messages about parties or candidates may include the name of the party or politician in either free text or as a hashtag. Tweets containing free text reference to political parties may be difficult to find in the Twitter data stream, as shown in Fig. 4, where although the tweet is clearly about SA Liberals, it was not directed to their Twitter account @LiberalSAHQ; however, the tweet is available in the Twitter feeds for #auspol (Australian politics) and #saparli (South Australian Parliament).

The SA Liberals first response to securing our energy future – it’s all about coal #auspol #saparli https://t.co/K5SiOeYVDm

Fig. 4 Tweet from Australian Labor Party, South Australia Branch (@alpsa) concerning the Liberal Party of Australia, 14-Mar-2017

Tweets from mediated events represent user interaction with television programs such as Q&A [12] or American Idol [13], an example of which uses the QandA hashtag is shown in Fig. 5, where a tweet from an organization user is made available to the Twitter feed #QandA (the Australian Broadcasting Corporation’s television program Q&A).

Ultimately the political class is distrustful of the arts because of sarcasm criticism ridicule of Govt decisions. #QandA

Fig. 5 Tweet from Seniors United Party of Australia (@AVoice4Seniors) using #QandA, 13-Mar-2017

  1. Adopting Technology

As technology changes, politicians have adapted to and adopted their use. For example, Roosevelt’s voice was a match for radio [14], Kennedy’s charisma commanded television [15], and Obama embraced Twitter [16]. The trend continues; all 17 Republican contenders for the presidential nomination used Twitter [17], with Donald Trump’s Twitter feed scoring highest on three constructs most likely to resonate with Republican voters: grandiosity, informality, and dynamism. A further study [3] observed that Trump’s mainly simple and repetitious, overwhelmingly negative and insulting tweets frequently use exclamation marks and words in capitalized forms.

  1. Prediction

Various trends in the areas of the economy, public opinion and population health have been identified by the predictive use of analytics on social media data; for example, using Google trends for financial trading [18] and internet searches [19]. Such mining is not perfect [20], and such models are modified as their results are compared to other sources of data. Twitter has been used to make predictions in areas such as: whether or not a movie will be successful [21], the marketability of consumer goods [22], the rise and fall of the stock market [23], and the location and spread of pandemics [24]. The success of using data from Twitter to make prediction in real-world activities led researchers to investigate the extent to which Twitter could be used to forecast election results.

  1. Predicting Election Results

Forecasting election results started with the 2009 German election, which concluded that the mere number of tweets about a party was a predictor of electoral success for that party [16] (i.e. it was unimportant whether or not the tweets were positive or negative; quantity was more important that quality). These results were soon rebutted [25] and the original authors offered a response to that criticism [26], watering down the predictive capabilities of their model. Thus, the debate the extent to which Twitter data could and should be used to forecast election results began. This debate is far from settled, although subsequent studies [27], [28], [29], [30], [31] have questioned the extent to which Twitter can provide accurate forecasting.

Following from that initial German study, data from Twitter has been used to predict elections in different countries, including: Brazil (2010): [32], France (2012) [33], Ireland (2011) [27], Italy (2011) [33], (2013) [34], Netherlands (2011) [28], New Zealand (2011) [35], Norway (2013) [11], Spain (2011) [36], Singapore (2011) [29], the United Kingdom (2010) [37], (2015) [38], and the United States of America (2010) [39], [36].

One concern with studies using data from Twitter is that most studies are post hoc and do produce true forecasts (results issued before the election) [40]. Indeed, on several occasions, election-related tweets have been subjected to post processing, with resulting claims that this data might have been able to make correct predictions [30]. By 2012, no paper had predicted a forward result [41]; however, a more recent paper [38] did make a forward prediction (and interestingly, that prediction was found be incorrect).

  1. Sourcing Data

The studies reviewed obtained their data from Twitter via a mixture of four methods, ranging in order of labor intensity: manually, using web-scrapes, using Twitter’s API, or utilizing third-party data sets. Manual transcription involves typing content from the Twitter website into a format useful for analysis. Web-scraping typically involves obtaining data in a format which must be cleaned in order to identify useful attributes. Using Twitter’s API allows data to be extracted into analysis tools such as R. Finally, third-party software products allow for complete data sets to be acquired.

A comparison of the results returned by various collection methods has not taken place [6]. For example, there is no agreed upon measure for ‘counting votes’: some studies count tweets, others count users, other perform (varying types of) sentiment analysis [41]. Thus, it is difficult to compare and contrast the merits of using one collection method over another. Given the absence of rigor in collecting and analyzing Twitter data, Twitter studies risk being as meaningless as the 1936 Literary Digest presidential poll [42], whereby a privileged and non-representative sample of the population (Literary Digest subscribers with telephones) was used to unsuccessfully predict the results of the presidential election.

  1. Measuring Data

Moving beyond counting the mere number of tweets, later studies introduced various research methods to both complement and supplement simple statistics, including: adding candidate attributes [43], comparing number of user mentions on Twitter between two parties to measure ‘relative support’ [34], including statistical analysis, such as daily auto regressive integrated moving average analysis [37], and performing sentiment analysis of tweets [33], [31], [44], [45], [46], [47] (all of which had mixed results, depending on the methodology used). One study investigated sentiment analysis, specifically comparing tweets to print media [48], and showed that sentiment between the two media was generally unrelated. It must be emphasized, however, than even though simple sentiment analysis [31] claims to replicate consumer confidence and presidential job approval polls, [40] recommends avoiding simple sentiment analysis because of the high level of humor, sarcasm and double entendres plaguing political discourse.

Even statistically rigorous methods are subject to caveats. A study which statistically analyzed tweets from Italian and Bulgarian political parties [49] concluded that although the number of daily tweets follows a log-normal distribution, the strong fluctuations in the volume of daily tweets meant that predictions of electoral success were only possible by adjusting the period for which sent tweets were analyzed. Thus, by changing the date parameters for which analysis was undertaken, different results were obtained. Therefore, researches are able to obtain a desired result by cherry-picking the data, excluding tweets sent during period which do not conform with their a priori expectations.

Some studies claim a positive link between mentions and Twitter and result [32], [39], [43], [50], [51], [52]; while other studies [25], [47], [48], [53] claim that no such link exist. Indeed, using Twitter to predict elections has been found to be no better than chance [30]. Middle ground exists too, whereby if a relationship exists between Twitter use and electoral success, then it is an indirect relationship and is highly contextually dependent [6]. Even when impressive predictive capabilities are claimed, such as one study of tweets made by politicians claiming a win/loss rate of 88% accuracy [39], a closer look at the study shows the authors are correct in only 49 of the 63 election races studied, an accuracy closer to 78% [30].

  1. Non-Representative Sample

Reasons to use Twitter data include the ability to perform real-time analysis, knowledge that Twitter has more participants than can be sampled by traditional election polls, as well as an ease of collection when compared to traditional polling methods [34]. However, Twitter users are not a representative sample of the population [54], unlike samples which were traditionally used for election polls (although it must be acknowledged that if current polling methods are limited to land-line telephones, then the extent to which land-line telephone users are a representative sample of the current population is questionable). Thus, Twitter and election polls are not perfect substitutes. This fact is often overlooked; while one study mentions that the data available from Twitter streaming is a only a fraction of total Twitter activity (about 1% of total tweets at any one moment [11]), it does not observe that collecting Twitter data results in a non-representative sample of data from a non-representative sample of the population. As an old adage advises: two wrongs don’t make a right.

Another concern is that demographic data must be inferred from other data which is assumed to be correct. For example, first and last name may give clues to both gender and race / ethnicity. However, the name recorded in Twitter must be accurate in order for that inference to hold true. Also, most Twitter user profiles do not contain geolocation coordinates (i.e. latitude and longitude) [54], which means that location is unknowable. Even for user profiles which include a location, the stated location (a string which could represent city, state, country, or free text) must be translated into geolocation coordinates.

Two reasons could explain the population bias attributable to Twitter users [42]: Urban and young people were more likely to use Twitter than rural and older people. The former being more likely liberal in political opinion; the latter more likely conservative. Additionally, conservative (Republican) voters use Twitter less than liberal (Democratic) voters, or perhaps Republican voters are shy to publically express their political opinions. In interesting contrast, however, is that conservative (right-wing) hashtags are more actively used than progressive (left-wing) hashtags [55].

Other biases [41] include: An assumption that tweets are trustworthy (not propaganda, or from astroturfers / sock-puppets), and a self-selection bias which stems from the fact that tweeting is voluntary – only politically active users tweet about politics. Thus, there are differences in usage patterns between a vocal minority and a silent majority [56]. In addition, when looking at tweets made by political parties, Twitter use is more likely to be higher for opposition parties than by governing parties [57].

  1. Improved Forecasting

In order to develop a model capable of making predictions [30], how data from Twitter is collected and analyzed needs to be properly operationalized, for example:

  • Any model produced should be developed on an algorithm with clearly described input parameters, such that the algorithm is structured, systematic and reproducible for future studies.
  • Data-specific attributes should be explained before the election (not after, when there is a temptation to cherry-pick the data). For example: the reasons for the dates for which data is to be collected should be described, as should any data processing undertaken (such as how keywords and/or stop words were ascertained).
  • Studies which use social media such as Twitter as a source of data need to acknowledge that social media data is different to data from natural phenomena (e.g. social media data can be manipulated by propagandists)
  • Studies should form a testable theory on why and when the model makes predictions, rather than make post hoc explanations of what the model did.
  • Studies which develop models to predict future election results need to outperform baselines (e.g. many, sometimes over 90% of US elections are won by incumbents). A model which performs worse than baseline is not competent.
  • Researchers need to learn professional techniques from pollsters, and acknowledge that, perhaps, social media data collection does not currently allow for statistically reliable sampling. For example, [37] recommends that the polling industry learn to leverage knowledge of modern “wisdom of crowds” [58], without acknowledging that social media are not representative of the “crowd”.
  1. Conclusion

Many studies claim to predict election results; however, many of the studies relied on post hoc models developed after the election had taken place, and thus are not actually capable of making predictions. At best, these models show an ability to segment voter results; however, since many of these studies fail to accurately disclose their underlying methodology, the studies lack application to subsequent data sets.

Some studies have attempted to follow best practices and develop a priori models, and their results, largely, do demonstrate that these models do not provide predictive capabilities. Thus, while these models do not predict election results, they should be considered important steps because they demonstrate a methodological proof of concept.

However, that is not to say that predicting election results from Twitter is not possible; but one must draw the conclusion that predicting election results is not currently possible. Given that Twitter users are not a representative sample of the population, it should not be surprising that the tweets ascribed to these authors are themselves not particularly useful in making election predictions. Regardless, continued exploration of this area of research with improved models may lead to future results which have more veracity than the results provided by current models. Until then, Twitter should be a complementary source of data for deriving voter intentions, not the sole source of data for predicting election results.

References

[1] Twitter, ‘Twitter milestones’, 2017. [Online]. Available: https://about.twitter.com/company/press/milestones. [Accessed: 21-Mar-2017].

[2] Twitter, ‘TWITTER USAGE / COMPANY FACTS’, 2016. [Online]. Available: https://about.twitter.com/company. [Accessed: 31-Mar-2017].

[3] B. L. Ott, ‘The age of Twitter: Donald J. Trump and the politics of debasement’, Crit. Stud. Media Commun., vol. 34, no. 1, pp. 59–68, 2017.

[4] Real Press Sec Bot, ‘Real Press Sec.’, 2017. [Online]. Available: https://twitter.com/RealPressSecBot. [Accessed: 07-Jun-2017].

[5] J. Echeverría and S. Zhou, ‘The Star Wars’ botnet with> 350k Twitter bots’, ArXiv Prepr. ArXiv170102405, 2017.

[6] A. Jungherr, ‘Twitter use in election campaigns: A systematic literature review’, J. Inf. Technol. Polit., vol. 13, no. 1, pp. 72–91, 2016.

[7] J. Golbeck, J. M. Grimes, and A. Rogers, ‘Twitter use by the US Congress’, J. Am. Soc. Inf. Sci. Technol., vol. 61, no. 8, pp. 1612–1621, 2010.

[8] N. Jackson and D. Lilleker, ‘Microblogging, constituency service and impression management: UK MPs and the use of Twitter’, J. Legis. Stud., vol. 17, no. 1, pp. 86–105, 2011.

[9] Ø. Sæbø, ‘Understanding TwitterTM use among parliament representatives: A genre analysis’, in International Conference on Electronic Participation, 2011, pp. 1–12.

[10] L. Dang-Xuan, S. Stieglitz, J. Wladarsch, and C. Neuberger, ‘An investigation of influentials and the role of sentiment in political communication on Twitter during election periods’, Inf. Commun. Soc., vol. 16, no. 5, pp. 795–825, 2013.

[11] A. O. Larsson and Ø. Ihlen, ‘Birds of a feather flock together? Party leaders on Twitter during the 2013 Norwegian elections’, Eur. J. Commun., vol. 30, no. 6, pp. 666–681, 2015.

[12] A. Bruns and T. Highfield, ‘Political networks on Twitter: Tweeting the Queensland state election’, Inf. Commun. Soc., vol. 16, no. 5, pp. 667–691, 2013.

[13] F. Ciulla, D. Mocanu, A. Baronchelli, B. Gonçalves, N. Perra, and A. Vespignani, ‘Beating the news using social media: the case study of American Idol’, EPJ Data Sci., vol. 1, no. 1, p. 8, 2012.

[14] P. F. Lazarsfeld, B. Berelson, and H. Gaudet, ‘The peoples choice: how the voter makes up his mind in a presidential campaign.’, 1968.

[15] P. J. Tichenor, G. A. Donohue, and C. N. Olien, ‘Mass media flow and differential growth in knowledge’, Public Opin. Q., vol. 34, no. 2, pp. 159–170, 1970.

[16] A. Tumasjan, T. O. Sprenger, P. G. Sandner, and I. M. Welpe, ‘Predicting elections with twitter: What 140 characters reveal about political sentiment.’, ICWSM, vol. 10, no. 1, pp. 178–185, 2010.

[17] S. Ahmadian, S. Azarshahi, and D. L. Paulhus, ‘Explaining Donald Trump via communication style: Grandiosity, informality, and dynamism’, Personal. Individ. Differ., vol. 107, pp. 49–53, 2017.

[18] T. Preis, H. S. Moat, and H. E. Stanley, ‘Quantifying Trading Behavior in Financial Markets Using Google Trends’, Sci. Rep., vol. 3, p. 1684, Apr. 2013.

[19] J. Mellon, ‘Internet search data and issue salience: The properties of Google Trends as a measure of issue salience’, J. Elections Public Opin. Parties, vol. 24, no. 1, pp. 45–72, 2014.

[20] D. Butler, ‘When Google got flu wrong’, Nature, vol. 494, no. 7436, pp. 155–156, Feb. 2013.

[21] S. Asur and B. A. Huberman, ‘Predicting the Future With Social Media’, in Web Intelligence and Intelligent Agent Technology (WI-IAT), 2010 IEEE/WIC/ACM International Conference on, 2010, vol. 1, pp. 492–499.

[22] Y. Shimshoni, N. Efron, and Y. Matias, ‘On the predictability of search trends’, Google Res. Blog, 2009.

[23] J. Bollen, H. Mao, and X. Zeng, ‘Twitter mood predicts the stock market’, J. Comput. Sci., vol. 2, no. 1, pp. 1–8, 2011.

[24] V. Lampos and N. Cristianini, ‘Tracking the flu pandemic by monitoring the social web’, in Cognitive Information Processing (CIP), 2010 2nd International Workshop on, 2010, pp. 411–416.

[25] A. Jungherr, P. Jürgens, and H. Schoen, ‘Why the Pirate Party Won the German Election of 2009 or The Trouble With Predictions: A Response to Tumasjan, A., Sprenger, T. O., Sander, P. G., & Welpe, I. M. “Predicting Elections With Twitter: What 140 Characters Reveal About Political Sentiment”’, Soc. Sci. Comput. Rev., vol. 30, no. 2, pp. 229–234, 2012.

[26] A. Tumasjan, T. O. Sprenger, P. G. Sandner, and I. M. Welpe, ‘Where There is a Sea There Are Pirates: Response to Jungherr, Jürgens, and Schoen’, Soc. Sci. Comput. Rev., vol. 30, no. 2, pp. 235–239, 2012.

[27] A. Bermingham and A. F. Smeaton, ‘On using Twitter to monitor political sentiment and predict election results’, 2011.

[28] E. T. K. Sang and J. Bos, ‘Predicting the 2011 Dutch senate election results with twitter’, in Proceedings of the workshop on semantic analysis in social media, 2012, pp. 53–60.

[29] M. Skoric, N. Poor, P. Achananuparp, E.-P. Lim, and J. Jiang, ‘Tweets and Votes: A Study of the 2011 Singapore General Election’, in System Science (HICSS), 2012 45th Hawaii International Conference on, 2012, pp. 2583–2591.

[30] P. T. Metaxas, E. Mustafaraj, and D. Gayo-Avello, ‘How (not) to predict elections’, in Privacy, Security, Risk and Trust (PASSAT) and 2011 IEEE Third Inernational Conference on Social Computing (SocialCom), 2011 IEEE Third International Conference on, 2011, pp. 165–171.

[31] B. O’Connor, R. Balasubramanyan, B. R. Routledge, and N. A. Smith, ‘From tweets to polls: Linking text sentiment to public opinion time series.’, ICWSM, vol. 11, no. 122–129, pp. 1–2, 2010.

[32] J. Gilmore, ‘Ditching the pack: Digital media in the 2010 Brazilian congressional campaigns’, New Media Soc., vol. 14, no. 4, pp. 617–633, 2012.

[33] A. Ceron, L. Curini, S. M. Iacus, and G. Porro, ‘Every tweet counts? How sentiment analysis of social media can improve our knowledge of citizens’ political preferences with an application to Italy and France’, New Media Soc., vol. 16, no. 2, pp. 340–358, 2014.

[34] G. Caldarelli et al., ‘A multi-level geographical study of Italian political elections from Twitter data’, PloS One, vol. 9, no. 5, p. e95809, 2014.

[35] M. P. Cameron, P. Barrett, and B. Stewardson, ‘Can Social Media Predict Election Results? Evidence From New Zealand’, J. Polit. Mark., vol. 15, no. 4, pp. 416–432, 2016.

[36] J. Borondo, A. Morales, J. C. Losada, and R. M. Benito, ‘Characterizing and modeling an electoral campaign in the context of Twitter: 2011 Spanish Presidential election as a case study’, Chaos Interdiscip. J. Nonlinear Sci., vol. 22, no. 2, p. 23138, 2012.

[37] F. Franch, ‘(Wisdom of the Crowds) 2: 2010 UK election prediction with social media’, J. Inf. Technol. Polit., vol. 10, no. 1, pp. 57–71, 2013.

[38] P. Burnap, R. Gibson, L. Sloan, R. Southern, and M. Williams, ‘140 characters to victory?: Using Twitter to predict the UK 2015 General Election’, Elect. Stud., vol. 41, pp. 230–233, 2016.

[39] A. Livne, M. P. Simmons, E. Adar, and L. A. Adamic, ‘The Party Is Over Here: Structure and Content in the 2010 Election.’, ICWSM, vol. 11, pp. 17–21, 2011.

[40] D. Gayo Avello, P. T. Metaxas, and E. Mustafaraj, ‘Limits of electoral predictions using twitter’, in Proceedings of the Fifth International AAAI Conference on Weblogs and Social Media, 2011.

[41] D. Gayo-Avello, ‘“I Wanted to Predict Elections with Twitter and all I got was this Lousy Paper”–A Balanced Survey on Election Prediction using Twitter Data’, ArXiv Prepr. ArXiv12046441, 2012.

[42] D. Gayo-Avello, ‘Don’t turn social media into another “Literary Digest” poll’, Commun. ACM, vol. 54, no. 10, pp. 121–128, 2011.

[43] J. DiGrazia, K. McKelvey, J. Bollen, and F. Rojas, ‘More tweets, more votes: Social media as a quantitative indicator of political behavior’, PloS One, vol. 8, no. 11, p. e79449, 2013.

[44] A. Agarwal, B. Xie, I. Vovsha, O. Rambow, and R. Passonneau, ‘Sentiment analysis of Twitter data’, in Proceedings of the workshop on languages in social media, 2011, pp. 30–38.

[45] J. Bollen, H. Mao, and A. Pepe, ‘Modeling public mood and emotion: Twitter sentiment and socio-economic phenomena.’, ICWSM, vol. 11, pp. 450–453, 2011.

[46] B. J. Jansen, M. Zhang, K. Sobel, and A. Chowdury, ‘Twitter power: Tweets as electronic word of mouth’, J. Am. Soc. Inf. Sci. Technol., vol. 60, no. 11, pp. 2169–2188, 2009.

[47] Y. Mejova, P. Srinivasan, and B. Boynton, ‘GOP primary season on Twitter: “Popula” Political Sentiment in Social Media’, in Proceedings of the sixth ACM international conference on Web search and data mining, 2013, pp. 517–526.

[48] D. Murthy and L. R. Petto, ‘Comparing Print Coverage and Tweets in Elections: A Case Study of the 2011–2012 US Republican Primaries’, Soc. Sci. Comput. Rev., vol. 33, no. 3, pp. 298–314, 2015.

[49] Y.-H. Eom, M. Puliga, J. Smailović, I. Mozetič, and G. Caldarelli, ‘Twitter-based analysis of the dynamics of collective attention to political parties’, PloS One, vol. 10, no. 7, p. e0131184, 2015.

[50] H. L. LaMarre and Y. Suzuki-Lambrecht, ‘Tweeting democracy? Examining Twitter as an online public relations strategy for congressional campaigns’’, Public Relat. Rev., vol. 39, no. 4, pp. 360–368, 2013.

[51] S. Kruikemeier, ‘How political candidates use Twitter and the impact on votes’, Comput. Hum. Behav., vol. 34, pp. 131–139, 2014.

[52] K. McKelvey, J. DiGrazia, and F. Rojas, ‘Twitter publics: How online political communities signaled electoral outcomes in the 2010 US house election’, Inf. Commun. Soc., vol. 17, no. 4, pp. 436–450, 2014.

[53] M. Vergeer, L. Hermans, and S. Sams, ‘Is the voter only a tweet away? Micro blogging during the 2009 European Parliament election campaign in the Netherlands’, First Monday, vol. 16, no. 8, 2011.

[54] A. Mislove, S. Lehmann, Y.-Y. Ahn, J.-P. Onnela, and J. N. Rosenquist, ‘Understanding the Demographics of Twitter Users.’, ICWSM, vol. 11, p. 5th, 2011.

[55] M. D. Conover, B. Gonçalves, A. Flammini, and F. Menczer, ‘Partisan asymmetries in online political activity’, EPJ Data Sci., vol. 1, no. 1, p. 6, 2012.

[56] E. Mustafaraj, S. Finn, C. Whitlock, and P. T. Metaxas, ‘Vocal minority versus silent majority: Discovering the opionions of the long tail’, in Privacy, Security, Risk and Trust (PASSAT) and 2011 IEEE Third Inernational Conference on Social Computing (SocialCom), 2011 IEEE Third International Conference on, 2011, pp. 103–110.

[57] S. Ahmed, K. Jaidka, and J. Cho, ‘The 2014 Indian elections on Twitter: A comparison of campaign strategies of political parties’, Telemat. Inform., vol. 33, no. 4, pp. 1071–1087, 2016.

[58] J. Surowiecki, ‘The wisdom of crowds: Why the many are smarter than the few and how collective wisdom shapes business’, Econ. Soc. Nations, vol. 296, 2004.

The post Twitter is an easy to use source of data appeared first on My Assignment Online.

Plagiarism Free Assignment Help

Expert Help With This Assignment — On Your Terms

✓ Native UK, USA & Australia writers ✓ Deadline from 3 hours ✓ 100% Plagiarism-Free — Turnitin included ✓ Unlimited free revisions ✓ Free to submit — compare quotes

admin

Academic writer and editor at BestWriters.

Get your paper off your plate tonight

Post your instructions for free. Prices start at $5 per page.

Place an order