Twitter paper-of-the-day

Is social media a valid indicator of political behavior? We answer this question using a random sample of 537,231,508 tweets from August 1 to November 1, 2010 and data from 406 competitive U.S. congressional elections provided by the Federal Election Commission. Our results show that the percentage of Republican-candidate name mentions correlates with the Republican vote margin in the subsequent election. This finding persists even when controlling for incumbency, district partisanship, media coverage of the race, time, and demographic variables such as the district’s racial and gender composition. With over 500 million active users in 2012, Twitter now represents a new frontier for the study of human behavior. This research provides a framework for incorporating this emerging medium into the computational social science toolkit.

From a new paper by DiGrazia et al (February 2013). The title: "More Tweets, More Votes: Social Media as a Quantitative Indicator of Political Behavior."

Twitter Used to Generate a Political Landscape of News Sources

That is from the paper by An et al (2012), "Twitter follow links reveal bicameral landscape of newspapers." The authors explain: 

This paper presented a first-of-its-kind, although preliminary study of the political media landscape of Twitter. We proposed a novel algorithm that generates a political di- chotomy map of media sources on Twitter, which is based on gathering online data and aggregating it via a closeness measure, without any complex procedures unlike in the past. Furthermore the ideological map of a particular issue can be created in real time in conjunction with a public stream of tweets from Twitter. Extending this work, we are currently examining how news media sources of different po- litical slants cover the same news story by conducting topic classification on news articles that are shared on Twitter.

We observed that the political dichotomy naturally arises on Twitter when we only consider direct media subscription. It implies that Twitter user may live in political echo-chamber. It is said that individuals need to have access to a pool of multiple points of view against which they can contrast their own values and belief as it helps them shape their eventual opinion. Nonetheless, we deemphasize the potential benefit of such political diversity because not ev- eryone prefers to receive diverse political opinions (Munson and Resnick 2010). Hence different strategies are required to assist heterogeneous individuals when news aggregators plan to increase opinion diversity. We hope to build a real- time platform that helps people receive balanced news information based on the proposed model that tracks bias in news in the future.

Important paper, innovative method, and numberless possibilities of applications and replications.  

Twitter and French elections

French law prohibits the publication, by the media or any Internet-connected citizen, of voting results or estimates before 8 p.m. on election days in the presidential race. The best-laid plans could not stop Twitter, though, whose users skirted regulations with offbeat code words and communicated tallies ahead of the appointed hour on Sunday.

Example:

. . . [T]he flan was decidedly in the oven, while the tomato was surprisingly green. By the same token — according to Twitter, at any rate — the temperature in Budapest hovered near 25 degrees.

Read the shot article by Scott Sayare in the NYT. 

Twitter graph-of-the-day

The graph is from the new paper "Geographic Dissection of the Twitter Network" Juhi Kulshrestha et al (2012). It concludes:

In this paper, we attempted to address the question: does of- fline geography still matter in online social networks? To this end, we dissected the Twitter social network based on users’ geolocations and investigated how users’ geoloca- tions impact their participation in Twitter, their connectivity with other users, and the information they exchange with them. Our in-depth analysis reveals that geography crucially impacts all aspects of the Twitter social network. Specifically, we find that even though users preferentially con- nect and exchange information with other users from their own country, more than a third of all links and tweets are exchanged across national boundaries. Such transnational links and interactions occur between users in geographically and linguistically proximal countries. Our findings have potential applications in predicting or recommending social connections for a user as well as in understanding global diffusion of information.

Twitter abstract of the day

By performing simple filtering and normalization, we demonstrate that Twitter can serve as a self-reporting tool, and hence, provide indications of increased infection spreading. Our initial findings indicate that Twitter can detect such events up to one week before conventional GP reported surveillance data.

That is from the abstract of the paper "Swineflu: Twitter predicts swine flu oubreak in 2009" by Szomszor, Kostkova, and De Quincey (2012).

Twitter in the classroom

The case of Ashesi University in Ghana is interesting:

In the Quantitative Methods class, Edward came up with a hashtag that he and Andrew use to curate tweets for the class. “I constantly monitor the class hashtag, and make sure I respond to questions from students as soon as I see them. It is a quick way to help students with problems with their assignments and class projects, and to get involved with them when they’re having study group discussions.” Dr. Larssen however, is encouraging students to tweet during class as well, not just out of class. 

For her Software Engineering class for example, members are allowed and encouraged to tweet questions and comments about the class content or the lecture while the class is ongoing. She then addresses the questions either verbally (or on Twitter) or after class. “I encourage the class to tweet their comments and questions using our class hashtag. I’ve noticed that students who otherwise are not too active in class contribute more.” [Italics added].

Source.

Twitter and the London Riots

The prolific commentary disseminated via Twitter on the riots in London and other British cities in August 2011 has given rise to the question of whether their reflection in such social media forums may have added to the unrest. Investigators analyzed 600,000 tweets and retweets about the riots for evidence that Twitter was used as a central organizational tool to promote illegal group action. Results indicated that irrelevant tweets died out and that Twitter users retweeted to show support for their beliefs in others’ commentaries. Tweets offered by well-known and popular individuals were more likely to be retweeted. In the case of the British riots, there is little overt evidence that Twitter was used to promote illegal activities at the time, though it was useful for spreading word about subsequent events.

That is the summary of the paper "Twitter, Information Sharing and the London Riots?" by Tonkin, Pfeiffer, and Tourte.

Crowd-sourced news

This is a great example on development economics. Twitter reshapes the industry again, and again, and again. 

Twitter mood predicts the stock market

This is a paper that came out in February 2011. It was written by Johan Bollen, Huina Mao, and Xiao-Jun Zeng. This is the abstract:

Behavioral economics tells us that emotions can profoundly affect individual behavior and decision-making. Does this also apply to societies at large, i.e. can societies experience mood states that affect their collective decision making? By extension is the public mood correlated or even predictive of economic indicators? Here we investigate whether measurements of collective mood states derived from large-scale Twitter feeds are correlated to the value of the Dow Jones Industrial Average (DJIA) over time. We analyze the text content of daily Twitter feeds by two mood tracking tools, namely OpinionFinder that measures positive vs. negative mood and Google-Profile of Mood States (GPOMS) that measures mood in terms of 6 dimensions (Calm, Alert, Sure, Vital, Kind, and Happy). We cross-validate the resulting mood time series by comparing their ability to detect the public's response to the presidential election and Thanksgiving day in 2008. A Granger causality analysis and a Self-Organizing Fuzzy Neural Network are then used to investigate the hypothesis that public mood states, as measured by the OpinionFinder and GPOMS mood time series, are predictive of changes in DJIA closing values. Our results indicate that the accuracy of DJIA predictions can be significantly improved by the inclusion of specific public mood dimensions but not others. We find an accuracy of 86.7% in predicting the daily up and down changes in the closing values of the DJIA and a reduction of the Mean Average Percentage Error (MAPE) by more than 6%.

The complete paper is here. 

Using Twitter for Research Projects and Teaching

This is a good guide to use Twitter in general, and also for Twitter as a research tool: 

Tweet about each new publication, website update or new blog that the project completes. To gauge feedback, you could send a tweet that links to your research blog and ask your followers for their feedback and comments. 

For tweeting to work well, always make sure that an open-web full version or summary of every publication, conference presentation or talk at an event is available online . . . 

Tweet about new developments of interest from the project’s point of view, for instance, relevant government policy changes, think tank reports, or journal articles. 

Use hashtags (#) to make your materials more visible – e.g. #phdchat. Don’t be afraid to start your own. 

Twitter provides many opportunities for ‘crowd sourcing’ research activities across the sciences, social sciences, history and literature – by getting people to help with gathering information, making observations, undertaking data analysis, transcribing and editing documents – all done just for the love of it. Some researchers have also used Twitter to help ‘crowdsource’ research funding from interested public bodies.You can read more about crowdsourcing at the LSE Impact blog. 

Read it all . . .

See also this article on how Twitter will revolutionize academic research and teaching. 

Twitter Paper of the day: Searching Twitter: Separating the Tweet from the Chaff

Within the millions of digital communications posted in online social networks, there is undoubtedly some valuable and useful information. Although a large portion of social media content is considered to be babble, research shows that people share useful links, provide recommendations to friends, answer questions, and solve problems. In this paper, we report on a qualitative investigation into the different factors that make tweets ‘useful’ and ‘not useful’ for a set of common search tasks. The investigation found 16 features that help make a tweet useful, noting that useful tweets often showed 2 or 3 of these features. ‘Not useful’ tweets, however, typically had only one of 17 clear and striking features. Further, we saw that these features can be weighted as according to different types of search tasks. Our results contribute a novel framework for extracting useful information from real-time streams of social-media content that will be used in the design of a future retrieval system. Read more . . .

This is the meat:

Results

Tables 3 and 4 give us an overview of the codes, grouped by category, that were derived from the data, for both the useful and not-useful collections, respectively. We saw four key reasons where the content of the tweet was directly useful. Some contained facts (e.g. times or prices) or increasingly common knowledge (e.g. problems with the iPhone). Others contained direct recommendations, or relayed insights from personal experiences. We also saw two types of tweets that the user found to be amenable, ones that were funny and ones that shared the searcher’s perspective (e.g. Apple products are good or bad). We also saw two codes that focused on whether tweets were geographically or temporally still relevant (e.g. tweets in British prices). We also saw a key theme of trust, where users reported approving of trusted twitter accounts and recognising trustable avatars for those accounts. Also, links to authoritative or trustworthy websites were frequently recognised. Other links were also important, whether they provided more detailed information, rich media, or services (e.g. buying tickets).

There were also five key reasons that the content of tweets was not useful for the searcher. First tweets were frequently vague or introspective (for the author), or were quite directly not relevant by topic. While some tweets showed potential, it was easy for tweets to be too technical for the reader (containing jargon) or to contain errors (e.g. malformed URLs). There were 3 other reasons for tweets to be badly constructed: containing dead links, spam-style content, and being in a foreign language.

Temporal patterns of happiness and information in a global social network

Temporal patterns of happiness and information in a global social network: Hedonometrics and Twitter

Abstract

Individual happiness is a fundamental societal metric. Normally measured through self-report, happiness has often been indirectly characterized and overshadowed by more readily quanti able economic indicators, such as gross domestic product. Here, we use a real-time, remote-sensing, noninvasive, text-based approach|a kind of hedonometer|to uncover collective dynamical patterns of happiness levels expressed by over 50 million users in the online, global social network Twitter. With a data set comprising nearly 2.8 billion expressions involving more than 28 billion words, we explore temporal variations in happiness, as well as information levels, over time scales of hours, days, and months. Among many observations, we nd a steady global happiness level, evidence of universal weekly and daily patterns of happiness and information, and that happiness and information levels are generally uncorrelated. We also extract and analyse a collection of happiness and information trends based on keywords, showing them to be both sensible and informative, and in effect generating opinion polls without asking questions. Finally, we develop and employ a graphical method that reveals how individual words contribute to changes in average happiness between any two texts.

It takes a little bit of time to make sense of the graphs . . . but it is worthy . . . just imagine the future . . .

Source