Tapping Twitter data for in-depth analysis of public opinion

September 20, 2013

Social scientists and others seeking insight into public opinion and behavior might benefit from Twitter-based research being conducted by two Arizona State University computer science doctoral students.

Yuheng Hu and Kartik Talamadupula are developing computer models for analytical systems that can harness massive amounts of data generated by Twitter and organize it in a rapid, reliable and efficient fashion. Twitter-based public opinion analysis Download Full Image

Such a capability can help provide a sound basis for advanced statistical analysis of public opinion that develops in reaction to various events or to the emergence of social and political issues and controversies.

Hu and Talamadupula are doing the research under the supervision of Subbarao Kambhampati, a professor in the School of Computer, Informatics, and Decision Systems Engineering, one of ASU’s Ira A. Fulton Schools of Engineering.

Kambhampati says the students’ research demonstrates how computer science can provide more sound information to help political scientists, social psychologists, linguists, journalists and others in similar fields gain more certainty in exploring societal attitudes and trends.

Gauging public reaction

Hu has created a computer model that performs a process he calls “sentiment analysis,” using data from Twitter messages to determine public reaction to various events. He tested the model during the presidential candidates’ debates before the 2012 national elections.

Hu’s system enabled him, for instance, to quickly determine whether there was a more positive or negative public reaction on Twitter to various comments made by the candidates.

Closely watched events such as political debates and campaign speeches generate thousands of tweets that indicate how the public feels about various subjects. But usually an analysis of Twitter messages is done manually, which provides only a limited sample of tweets with which to determine trends in public opinion.

Analysts “might be able to manually sort through 300 tweets to study language or analyze public sentiment, but they lose out on a lot of information and the process is inefficient,” Kambhampati explains.

Hu’s model can quickly segment and align tweets according to the content of the messages and what they express about events and issues, thus providing a more accurate gauge of public attitudes.

Twitter-based linguistics  

Hu teamed up with Talamadupula for a second project to conduct a computational linguistic analysis of the language used on Twitter. They were curious about whether the language of Twitter most resembles the way people communicate in text messages, e-mails or in the more formal language of magazines.

“All forms of social media and written publications have their own linguistic expectation,” Kambhampati says. Text messages contain language-shortening techniques, abbreviations and slang more frequently than e-mails, for instance.

“Linguists have been debating about the implications of the language of Twitter for some time, but Hu’s and Talamadupula’s research brings a needed large-scale analysis to the discussion,” he says.

Hu and Talamadupula conducted a computational linguistic analysis that took a “snapshot” from a portion of the Twitter fire hose from June to August in 2011. In this snapshot of thousands of tweets they found that the language tends to resemble e-mail and magazine language more than the language used in text messages.

Hu said they found Twitter language “surprisingly formal,” revealing that people resist word shortening and slang despite having to limit tweets to 140 characters.

New social science tool

Kambhampati says both projects exemplify the emergence of “computational social science,” a powerful tool for those in social science fields to more accurately analyze large amounts of data and provide a more solid basis for identifying or predicting trends in societal attitudes and behavior.

“Human behavior is dynamic and often hard to understand, this research has been a great opportunity to know people better through social media,” Hu says.  

Kambhampati says the analysis of social media – something that is used millions of times each day – gives researchers a more vast trove of data than standard polls and surveys from which to derive empirical evidence of public sentiment.

The kind of large-scale data offered by the computational methods Hu and Talamadupula are developing “is just the beginning” of advanced analytics that can have far-reaching impacts on sociological research, Kambhampati says.

Hu and Talamadupula presented their research at the International Conference of Weblogs and Social Media in Boston in July and Kambhampati made a presentation at the International Joint Conference on Artificial Intelligence in August in Beijing, China.

Emerging research field

In addition, Kambhampati recently received a $55,000 Google Research Award to support work related to the Twitter Alignment project. It is Kambhampati’s third Google Research Award.

He says the awards keep coming because Google respects the work ASU researchers are doing in this area and the company has an interest in the emerging field of “computational journalism” tied to Twitter.

“Reporting on Twitter and analyzing what is said are new and emerging areas of journalism,” says Kambhampati. “Our research clearly relates to that emerging field.”

Kambhampati plans to use the Google grant to expand research in “ways that we haven’t even fully realized yet.”

In addition to presenting the research at conferences, Hu spent his summer doing a Microsoft Research Internship in Washington state. He performed similar research focused on using Twitter to predict users engagement in local events.

In collaboration with Srijith Ravikumar, who is pursuing a master’s degree in computer science at ASU, Talamadupula began research on new algorithms to rank Twitter search results according to the interests of specific users. He reported on the research at the Annual Association for the Advancement of Artificial Intelligence (AAAI) conference in Washington state in July.

Their paper has also been accepted for presentation at the Association for Computing Machinery (ACM) International Conference on Information and Knowledge Management conference in San Francisco in October.

Written by Rosie Gochnour and Joe Kullman

Joe Kullman

Science writer, Ira A. Fulton Schools of Engineering


Professor 'thinks around the edges' of obesity problem

September 23, 2013

Research looks at complex interactions between human biology, culture

As an anthropology graduate student in the late 80s, Alexandra Brewis Slade carried out field projects in the Pacific Islands on women’s fertility and family planning. While Pacific Islanders at that time were among some of the most overweight populations on earth, she never heard obesity mentioned as a health problem even once. The islanders scolded her for being “too skinny” to attract a husband. Download Full Image

When she moved to expand a Samoan body image project at the University of Auckland in the early 90s, a colleague warned her that obesity was a marginal area for a social scientist to work in, a bit odd and freakish, and its explicit study was probably not the best career move.

Brewis Slade persisted, going on to study the cultural aspects of a high rate of school children’s obesity in rural Georgia and central Mexico, many of whom were at high risk for being obese. Now a widely-cited expert, she has been working on comparative studies of obesity, based on field research in a broad array of countries, such as Paraguay, New Zealand and Fiji.

The recipient of a Rockefeller Foundation pre-doctoral fellowship and an Andrew W. Mellon post-doctoral fellowship, she has published 55 papers and three books, including “Obesity: Cultural and Biocultural Perspectives” in 2011. She is director of ASU’s School of Human Evolution and Social Change and director of operations for the ASU-Mayo Obesity Solutions Initiative.

Brewis Slade notes that in a stunningly short time, obesity has gone from being considered an aberration in both popular culture and scientific circles to being perceived as a massive global threat. Unlike many global calamities such as climate change, no one seemed to notice the dramatic rise in obesity until it was well under way.

“Obesity is arguably one of the greatest public health challenges we face, infiltrating almost every aspect of our lives,” says Brewis Slade. “It shapes whether we get into college, the job offers and promotions we get, how much money we make, our access to health care, our romantic relationships. We are bombarded in the media with messages about the need to be slim and lose weight.

“We associate obesity with moral failure, with a lack of control, laziness and lack of ambition. The stigma of being obese is profound, and it causes tremendous emotional suffering. The social cost is just as important to address as the health cost.”

Cruel comments about weight are socially acceptable in many circles, and are a leading factor in childhood bullying, she says.

She also has found that globalization has spread the stigma associated with obesity from the western world to other parts of the world, including regions that previously viewed large body size in a neutral or positive light. Her research shows that negative media and public health messages about obesity are so powerful that they overshadow the positive support of family and friends in shaping how people feel about their large body size.

Her most recent work on obesity-related stigma particularly appears to have hit a cultural nerve. Her comment, “Of all the things we could be exporting to help people around the world, really negative body image and low self-esteem are not what we hope is going out with public health messaging,” was quote of the day in the New York Times and was mentioned on NBC’s “Saturday Night Live,” which she notes with good humor.

Her research team’s work on obesity also has focused on university students, based on research conducted at ASU.

They have confirmed that obesity is socially contagious and the risk of a woman’s obesity rises if her friends and family members are obese. Shared eating and exercising habits may have the strongest correlation. Currently, her team is working with a start-up company to design ways of using smart phones to connect friends and family to exercise together.

“There are lots of reasons why we gain weight and we know that telling people to ‘eat less and exercise more’ doesn’t work. We’re swimming upstream with that approach because people are working long hours, they don’t have time to exercise or make home-cooked meals. We have to look at what’s possible to change.

“Instead of blaming people for their condition, we need to step back and look at the structure of our cities, our neighborhoods, our schools and our campuses, that shape health at every level.”

She works with ASU students enrolled in research practicum classes to do research on the campus, such as surveys, focus groups and interviews with other students. Fat stigma is surprisingly high at ASU, she says; about 20 percent of students would rather be blind than obese. Her work with undergraduates has a view to designing more healthful campuses, from the perspective of people’s norms and behaviors related to weight, exercise and nutrition.

Brewis Slade’s research is ultimately concerned with the complex interactions between human biology and culture, looking at human health in the context of massive transformational processes, such as globalization and climate change. She enjoys working in diverse collaborative teams, a factor that led her to join ASU in 2006.

“ASU is a fantastic place for someone like me who thinks around the edges of problems,” she says. “I’m inspired and invigorated by the transdisciplinary environment at ASU. It’s an energetic, exciting place and I can’t think of anywhere else I’d rather be.”

She believes the partnership with Mayo makes it possible, for the first time, for a university to think of tackling the challenge of obesity on a global scale.

“What makes ASU able to attempt this is the comprehensive nature of our expertise, and the scale and scope of our collective research. We have people with talent and expertise that can be applied to almost any aspect of the complicated problem of obesity, from the built environment, to food choices, to genetics. ASU’s coverage is unmatched in the volume of different ways we can devise to tackle the problem.

“Partnering with Mayo gives us additional access to talent in the medical understanding and treatment of obesity. This provides us with a truly massive shared toolkit to address the complicated challenge of obesity.”

The School of Human Evolution and Social Change is an academic unit in ASU's College of Liberal Arts and Sciences.