Twitter, a microblogging service less than three years old, commands more than 41 million users as of July 2009 and is growing fast. Twitter users tweet about any topic within the 140-character limit and follow others to receive their tweets. The goal of this paper is to study the topological characteristics of Twitter and its power as a new medium of information sharing.We have crawled the entire Twitter site and obtained 41.7 million user profiles, 1.47 billion social relations, 4,262 trending topics, and 106 million tweets. In its follower-following topology analysis we have found a non-power-law follower distribution, a short effective diameter, and low reciprocity, which all mark a deviation from known characteristics of human social networks [28]. In order to identify influentials on Twitter, we have ranked users by the number of followers and by PageRank and found two rankings to be similar. Ranking by retweets differs from the previous two rankings, indicating a gap in influence inferred from the number of followers and that from the popularity of one's tweets. We have analyzed the tweets of top trending topics and reported on their temporal behavior and user participation. We have classified the trending topics based on the active period and the tweets and show that the majority (over 85%) of topics are headline news or persistent news in nature. A closer look at retweets reveals that any retweeted tweet is to reach an average of 1,000 users no matter what the number of followers is of the original tweet. Once retweeted, a tweet gets retweeted almost instantly on next hops, signifying fast diffusion of information after the 1st retweet.To the best of our knowledge this work is the first quantitative study on the entire Twittersphere and information diffusion on it.

https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=7104&context=sis_research

What is Twitter, a social network or a news media?

Twitter, a popular microblogging service, has received much attention recently. An important characteristic of Twitter is its real-time nature. For example, when an earthquake occurs, people make many Twitter posts (tweets) related to the earthquake, which enables detection of earthquake occurrence promptly, simply by observing the tweets. As described in this paper, we investigate the real-time interaction of events such as earthquakes in Twitter and propose an algorithm to monitor tweets and to detect a target event. To detect a target event, we devise a classifier of tweets based on features such as the keywords in a tweet, the number of words, and their context. Subsequently, we produce a probabilistic spatiotemporal model for the target event that can find the center and the trajectory of the event location. We consider each Twitter user as a sensor and apply Kalman filtering and particle filtering, which are widely used for location estimation in ubiquitous/pervasive computing. The particle filter works better than other comparable methods for estimating the centers of earthquakes and the trajectories of typhoons. As an application, we construct an earthquake reporting system in Japan. Because of the numerous earthquakes and the large number of Twitter users throughout the country, we can detect an earthquake with high probability (96% of earthquakes of Japan Meteorological Agency (JMA) seismic intensity scale 3 or more are detected) merely by monitoring tweets. Our system detects earthquakes promptly and sends e-mails to registered users. Notification is delivered much faster than the announcements that are broadcast by the JMA.

/pdf/earthquake-shakes-twitter-users-real-time-event-detection-by-1tue7cvj9p.pdf

Earthquake shakes Twitter users: real-time event detection by social sensors

行銷硏究 : Marketing research

Twitter is a microblogging website where users read and write millions of short messages on a variety of topics every day This study uses the context of the German federal election to investigate whether Twitter is used as a forum for political deliberation and whether online messages on Twitter validly mirror offline political sentiment Using LIWC text analysis software, we conducted a content-analysis of over 100,000 messages containing a reference to either a political party or a politician Our results show that Twitter is indeed used extensively for political deliberation We find that the mere number of messages mentioning a party reflects the election result Moreover, joint mentions of two parties are in line with real world political ties and coalitions An analysis of the tweets’ political sentiment demonstrates close correspondence to the parties' and politicians’ political positions indicating that the content of Twitter messages plausibly reflects the offline political landscape We discuss the use of microblogging message content as a valid indicator of political sentiment and derive suggestions for further research

/pdf/predicting-elections-with-twitter-what-140-characters-reveal-5bagzv2skv.pdf

Predicting Elections with Twitter: What 140 Characters Reveal about Political Sentiment

Microblogging today has become a very popular communication tool among Internet users. Millions of users share opinions on different aspects of life everyday. Therefore microblogging web-sites are rich sources of data for opinion mining and sentiment analysis. Because microblogging has appeared relatively recently, there are a few research works that were devoted to this topic. In our paper, we focus on using Twitter, the most popular microblogging platform, for the task of sentiment analysis. We show how to automatically collect a corpus for sentiment analysis and opinion mining purposes. We perform linguistic analysis of the collected corpus and explain discovered phenomena. Using the corpus, we build a sentiment classifier, that is able to determine positive, negative and neutral sentiments for a document. Experimental evaluations show that our proposed techniques are efficient and performs better than previously proposed methods. In our research, we worked with English, however, the proposed technique can be used with any other language.

/pdf/twitter-as-a-corpus-for-sentiment-analysis-and-opinion-zxo77yicta.pdf

Twitter as a Corpus for Sentiment Analysis and Opinion Mining

In this paper we report research results investigating microblogging as a form of electronic word-of-mouth for sharing consumer opinions concerning brands. We analyzed more than 150,000 microblog postings containing branding comments, sentiments, and opinions. We investigated the overall structure of these microblog postings, the types of expressions, and the movement in positive or negative sentiment. We compared automated methods of classifying sentiment in these microblogs with manual coding. Using a case study approach, we analyzed the range, frequency, timing, and content of tweets in a corporate account. Our research findings show that 19p of microblogs contain mention of a brand. Of the branding microblogs, nearly 20p contained some expression of brand sentiments. Of these, more than 50p were positive and 33p were critical of the company or product. Our comparison of automated and manual coding showed no significant differences between the two approaches. In analyzing microblogs for structure and composition, the linguistic structure of tweets approximate the linguistic patterns of natural language expressions. We find that microblogging is an online tool for customer word of mouth communications and discuss the implications for corporations using microblogging as part of their overall marketing strategy. © 2009 Wiley Periodicals, Inc.

/pdf/twitter-power-tweets-as-electronic-word-of-mouth-3yfo7qbk2k.pdf

Twitter power: Tweets as electronic word of mouth

In this paper, we report research results investigating micro-blogging as a form of online word of mouth branding. We analyzed 149,472 micro-blog postings containing branding comments, sentiments, and opinions. We investigated the overall structure of these micro-blog postings, types of expressions, and sentiment fluctuations. Of the branding micro-blogs, nearly 20 percent contained some expressions of branding sentiments. Of these tweets with sentiments, more than 50 percent were positive and 33 percent critical of the company or product. We discuss the implications for organizations in using micro-blogging as part of their overall marketing strategy and branding campaigns.

/pdf/micro-blogging-as-online-word-of-mouth-branding-3dopx85pck.pdf

Micro-blogging as online word of mouth branding

Social media services, such as Twitter, enable commercial businesses to participate actively in online word-of-mouth communication. In this project, we examined the potential influences of business engagement in online word-of-mouth communication on the level of consumers’ engagement and investigated the trajectories of a business’ online word-of-mouth message diffusion in the Twitter community. We used path analysis to examine 164,478 tweets from 96,725 individual Twitter users with regards to nine brands during a 5-week study period. We operationalized business engagement as the amount of online word-of-mouth messages from brand and the number of consumers the brand follows. We operationalized consumers’ engagement as the number of online word-of-mouth messages from consumers both connecting to the brand and having no connection with the brand as well as the number of consumers following the brand. We concluded that the business engagement on Twitter relates directly to consumers’ engagement with online word-of-mouth communication. In addition, retweeting, as an explicit way to show consumers’ response to business engagement, indicates that the influence only reaches consumers with a second-degree relationship to the brand and that the life cycle of a tweet is generally 1.5 to 4 hours at most. Our research has critical implications in terms of advancing the understanding of the business’s role in the online word-of-mouth communication and bringing insight to the analytics of social networks and online word-of-mouth message diffusion patterns.

/pdf/business-engagement-on-twitter-a-path-analysis-3e2hlh1shu.pdf

Business engagement on Twitter: a path analysis

In this paper, we analyze the relationship between performance and use of brand terms in the key phrases that link advertisements to searcher queries. We use data that consist of more than 2.5 million daily records from a key word advertising campaign of a major U.S. retailer. The campaign spanned nearly four years, involved approximately $8 million in advertising cost, and generated more than $23 million in sales. We categorize key phrases and advertisements as either brand focused or non-brand focused. Using analysis of variance in a 2 ii¾? 2 design, we analyze use of branded terms on the critical key word advertising metrics of number of clicks, cost per click, sales revenue generated, number of orders, number of items ordered, and return on advertising cost, as well as number of impressions triggered by these key phrases. Therefore, we investigate a significant spectrum of user actions and consumer behaviors in a sponsored search campaign. Our findings show that there is a significant advantage to matching branding terms in key phrases and advertisements relative to any other combination of key phrase or advertisement for all the metrics examined. A combination of a branded phrase and a branded advertisement generated 15 times more sales revenue than any other combination of phrase and advertisement. Therefore, a focus by key word advertisers on branded terms for search engine ads could be quite beneficial for both the effectiveness and efficiency of key word advertising. The implication for online advertising and key word search in the e-commerce domain, especially for large retailers, is that brand mentions in both key phrase and advertisements correlate with higher conversions.

/pdf/the-brand-effect-of-key-phrases-and-advertisements-in-37z70ntfjd.pdf

The Brand Effect of Key Phrases and Advertisements in Sponsored Search

In this research we investigate the effect of search engine brand on the evaluation of searching performance. Our research is motivated by the large amount of search traffic directed to a handful of Web search engines, even though many have similar interfaces and performance. We conducted a laboratory experiment with 32 participants using a 42 factorial design confounded in four blocks to measure the effect of four search engine brands (Google, MSN, Yahooe, and a locally developed search engine) while controlling for the quality and presentation of search engine results. We found brand indeed played a role in the searching process. Brand effect varied in different domains. Users seemed to place a high degree of trust in major search engine brands; however, they were more engaged in the searching process when using lesser-known search engines. It appears that branding affects overall Web search at four stages: (a) search engine selection, (b) search engine results page evaluation, (c) individual link evaluation, and (d) evaluation of the landing page. We discuss the implications for search engine marketing and the design of empirical studies measuring search engine performance. © 2009 Wiley Periodicals, Inc.

/pdf/brand-and-its-effect-on-user-perception-of-search-engine-2kjtxyhq7g.pdf

Mimi Zhang

Papers

Twitter power: Tweets as electronic word of mouth

Micro-blogging as online word of mouth branding

Business engagement on Twitter: a path analysis

The Brand Effect of Key Phrases and Advertisements in Sponsored Search

Brand and its effect on user perception of search engine performance