Eni Mustafaraj

Social Media and the Elections

Manipulation of social media affects perceptions of candidates and compromises decision-making. In the United States, social media sites—such as Facebook, Twitter, and YouTube—are currently being used by two out of three people (1), and search engines are used daily (2). Monitoring what users share or search for in social media and on the Web has led to greater insights into what people care about or pay attention to at any moment in time. Furthermore, it is also helping segments of the world population to be informed, to organize, and to react rapidly. However, social media and search results can be readily manipulated, which is something that has been underappreciated by the press and the general public.

Vocal Minority Versus Silent Majority: Discovering the Opionions of the Long Tail

Social networks such as Face book and Twitter have become the favorite places on the Web where people discuss real-time events. In fact, search engines such as Google and Bing have special agreements, which allow them to include into their search results public conversations happening in real-time in these social networks. However, for anyone who only reads these conversations occasionally, it is difficult to evaluate the (often) complex context in which these conversation bits are embedded. Who are the people carrying on the conversation? Are they random participants or people with a specific agenda? Making sense of real-time social streams often requires much more information than what is visible in the messages themselves. In this paper, we study this phenomenon in the context of one political event: a special election for the US Senate which took place in Massachusetts in January 2010, as observed in conversations on Twitter. We present results of data analysis that compares two groups of different users: the vocal minority (users who tweet very often) and the silent majority (users who tweeted only once). We discover that the content generated by these two groups is significantly different, therefore, researchers should take care in separating them when trying to create predictive models based on aggregated data.

Using TwitterTrails.com to Investigate Rumor Propagation

Social media have become part of modern news reporting, used by journalists to spread information and find sources, or as a news source by individuals. The quest for prominence and recognition on social media sites like Twitter can sometimes eclipse accuracy and lead to the spread of false information. As a way to study and react to this trend, we demo TWITTERTRAILS, an interactive, web-based tool (twittertrails.com) that allows users to investigate the origin and propagation characteristics of a rumor and its refutation, if any, on Twitter. Visualizations of burst activity, propagation timeline, retweet and co-retweeted networks help its users trace the spread of a story. Within minutes TWITTERTRAILS will collect relevant tweets and automatically answer several important questions regarding a rumor: its originator, burst characteristics, propagators and main actors according to the audience. In addition, it will compute and report the rumors level of visibility and, as an example of the power of crowdsourcing, the audiences skepticism towards it which correlates with the rumors credibility. We envision TWITTERTRAILS as valuable tool for individual use, and especially for amateur and professional journalists investigating recent and breaking stories.

The Use of Online Videos in the 2008 U.S. Congressional Elections

In a recent survey, 39% of Americans reported using the Web to access campaign materials for the 2008 primary elections. Assuming they are using popular search engines such as Google, it is important to investigate their search patterns and ensure that standards of fairness and balanced coverage are upheld in the results. In this paper, we offer an exploratory analysis of political online video data. This data was collected in the context of a broader project aimed at studying the effects of politically motivated spamming of webpages to manipulate their rankings within search engine results. Using online video parameters such as the submission date, number of views, ranking position, description keywords, political inclination of the submitter, the political message in the video, and commentsassociated with the video, we construct a picture of how online video medium was used during the last congressional political campaign. Our analysis takes into account three players: video providers (usually the campaigns or other interested parties), video consumers (the users), and search facilitators (Google and YouTube). The results indicate that online video coverage might be susceptible to technological bias that adds to the political biascommon in electoral campaigns. Educating the broader publicabout this inherent bias should be a common effort of the involved players and fairness advocacy groups.

Panel: mobile application development in computing curricula

Many institutions are considering offering a course on mobile application development to harness its popularity to attract new majors, retain those we have, and to motivate learning. The panelists present four experiences in teaching a mobile application development course. They share their experiences in an effort to start a discussion about mobile application development in computing curricula. In the first half of the session, each panelist presents their experience including: an overview of the course; its audience, position in the curriculum, and pre-requisites; the platform, language, and development environment used; positives about the course; and roadblocks and negatives about the course. This provides a foundation for an audience directed discussion in the second half.

New Quality Metrics for Web Search Results

Web search results enjoy an increasing importance in our daily lives. But what can be said about their quality, especially when querying a controversial issue? The traditional information retrieval metrics of precision and recall do not provide much insight in the case of web information retrieval. In this paper we examine new ways of evaluating quality in search results: coverage and independence. We give examples on how these new metrics can be calculated and what their values reveal regarding the two major search engines, Google and Yahoo. We have found evidence of low coverage for commercial and medical controversial queries, and high coverage for a political query that is highly contested. Given the fact that search engines are unwilling to tune their search results manually, except in a few cases that have become the source of bad publicity, low coverage and independence reveal the efforts of dedicated groups to manipulate the search results.

The Co-Retweeted Network and its Applications for Measuring the Perceived Political Polarization

This paper introduces a novel network, the co-retweeted network, that is constructed as the undirected weighted graph that connects highly visible accounts who have been retweeted by members of the audience during some real-time event. Like bibliographics co-citation used to indicate that two papers treat a related subject matter, co-retweeting is used to indicate that two accounts present similar opinions in an online discussion. Thus, the co-retweeted network can be seen as a form of consulting the opinion of the crowd that is following the discussion about the similarity (or difference) of positions expressed by the highly visible accounts. When applied on political conversations related to some event, the co-retweeted network enables the measurement of the polarity of political orientation of major players (including news organizations) based on the views of the audience. It can also measure the degree of polarization of the event itself.

Work in Progress: Identifying and Analyzing Original Projects in an Open-Ended Blocks Programming Environment.

Tens of millions of people have used online blocks programming environments like App Inventor to learn how to program and build personally meaningful programs and apps. We want to improve blocks programming environments and pedagogies by using learning analytics to identify common problems and then address them. For most users, there is no information about which projects are original (built from scratch by individuals or groups based on their own ideas and current programming skills) vs. unoriginal (based on tutorials, class exercises, etc.). To understand what App Inventor users are learning and what misconceptions they have, we need to filter out unoriginal projects and focus on original ones. Here we describe two key aspects of our work in progress towards this goal. First, we have developed feature-vector representations of App Inventor projects that formalize a notion of structural similarity between them. This representation facilitates filtering out unoriginal work like tutorials and can be used within a group of learners to distinguish classroom activities from original projects. Second, we have developed a graph clustering technique based on project creation timestamps to discover groups of App Inventor users that appear to be taking a course together — essential information for distinguishing original vs. unoriginal work that is not explicitly represented in our datasets.

What does enrollment in a MOOC mean

In 2012, when MOOCs became largely known, media reports were fascinated with the big number of enrollments. The number 150,000 students was mentioned for both Stanfords Artificial Intelligence course and MITs Circuits and Electronics, to be later followed by the underwhelming completion rates, that often are in the single digit percentages. But what kind of enrollment do these large numbers really show? We try to answer this question by breaking this number into its components, while comparing two successive iterations of the same MOOC offered on the edX platform.

Calls of the wild: Exploring procedural abstraction in app inventor

One of the most important computational concepts in any programming language is procedural abstraction. We investigate the use of procedures in MIT App Inventor, a web-based blocks programming environment for creating Android mobile apps. We explore how procedures are used “in the wild” by examining two datasets of App Inventor projects: all projects of ten thousand randomly chosen users and all projects of all prolific users (those users with 20 or more projects). Our data analysis indicates that procedural abstraction is a concept that is learned over time by some App Inventor users, but it is used relatively infrequently, and features like parameters and returning values are used even more rarely. Procedures are most frequently called only once, indicating that they are often used to organize code rather than to reuse it. Surprisingly, 10% of declared procedures are never called, suggesting that this situation should be flagged by the environment.