The PEARC Student Program brings together participants to learn technical skills, meet mentors, engage with fellow students, and build a strong foundation for their future career.

Which is why it’s important to step back once in a while and breathe—especially for young scientists just starting their careers.

This is why the PEARC (Practice and Experience in Research Computing) Student Program was created. Founded in 2009 and originally including only 8 students, the program blossomed into an operation that hosted 114 attendees at this summer’s PEARC19 conference in Chicago. 

Semir Sarajlic, a research scientist at Georgia Tech and the Student Program chair, believes a large part of this success comes from the organization’s desire to help students network.

“The Student Program actually focuses on the experience for students to come to a conference and be able to engage with other fellow students,” says Sarajlic. “They also meet mentors who have been in this field for years. These mentors share with the students and shepherd them along the way.” 

Many students have come and gone in the ten years since the program’s inception, but plenty come back to help the next generation. Science Node caught up with two previous participants who returned this year as student volunteers — a testament to the program’s lasting impact.

Building a community

One aspect of the Student Program that all participants praise is the significance of the mentor-mentee relationship. Alexa Salsbury, a graduate student at Virginia Tech working on her PhD in biochemistry, spoke about how mentors can help you get out of your comfort zone.

“They match you up with a mentor and you have lunch, coffee, and dinner with them,” says Salsbury. “It’s someone you see throughout the conference that isn’t from your home institution, and it forces you to get out a little bit.”

Mentors also guide students through their PEARC experience. From suggesting which informational sessions a student should attend to explaining complicated topics, the mentors form a foundation upon which a student can build their career.

However, the benefits of the mentor portion of the Student Program don’t end when the conference wraps up. Mohammad Tanash, who is working toward his PhD in computer science at Kansas State University, believes that these relationships even helped improve his research.

“Talking about my research to experts, I got lots of advice,” says Tanash. “I did some research on what they said to me, and I found it very useful and helpful. Even when talking to my advisor about my research, I gave him some ideas that I got from the people at the conference.”

Today’s science and engineering is all about collaboration. Whether it’s working with people from other universities or simply brainstorming with colleagues, modern scientists rely on their peers. The PEARC Student Program emphasizes the importance of working together and considering new perspectives.

A fun-friendly conference

Even though the PEARC Student Program is built around teaching and seeks to improve technological skills, the students we talked to were quick to point out that it’s also a really good time. 

“Having fun is very important, especially for students,” says Tanash. “We are spending lots of time in the lab, studying, and even sometimes not sleeping. Lots of stress. Usually we say, ‘In graduate school, there is no life.’ But actually, there is life. The Student Program is a good opportunity to have fun.”

The PEARC Student Program is an opportunity for students and researchers to push back against some widespread misconceptions: that scientists and technologists are boring.

“Everyone thinks that you’re going to come here and be with high-performance computing people, and everyone’s going to be looking at their computers,” says Salsbury. “But that’s not how it is at all. Everyone’s very friendly and talkative!”

As Sarajlic points out, it’s the combination of dedication to research and to fun that makes the PEARC Student Program such a unique and wonderful experience.

“It’s just so nice and heartwarming when you see groups of students huddled together trying to solve a problem, and creatively and collaboratively working together,” says Sarajlic. “That just goes to show that what we’re trying to do over here is actually working.”

This article was originally published on ScienceNode.org. Read the original article.

The post Get out of your comfort zone appeared first on PEARC20 - Catch the Wave.

No matter how you look at it, politicians lie. Most of us know that, but simply don’t have the time or energy to dig through their record and find the truth. 

But what if there were a tool that helped you choose which politician to vote for based solely on how well their beliefs align with the issues that matter to you? 

Dr. Srijith Rajamohan, a computational scientist at Virginia Tech, thinks this could be within reach. In fact, he’s working on a deep-learning based interactive visualization tool to understand and plot political ideologies based on Twitter activity. 

“Is there a way to extract and understand people’s ideologies from the things that they say?” asks Rajamohan. “I turned to natural language understanding to see if we can take text from social media, run it through a deep learning model, and find some way to quantify it.”

Someday soon, a tool like Rajamohan’s could have a huge impact on how people understand political ideologies. And if we’re lucky, it could make voting for the right candidate a lot easier.  

Cleaning up the data

The end-goal of this work was to construct a visualization tool that could help identify political ideology. However, as many important endeavors do, this project began with an intriguing conversation.

“It all started over coffee when Alana Romanella and I were discussing white supremacy and hate speech,” says Rajamohan. “The conversation evolved, and we started talking about different political groups.” 

Eventually, Romanella and Rajamohan decided they could use deep learning to better understand political ideology by investigating social media posts. They decided to focus on Twitter, as it is a data-rich environment with a free application programming interface (API). After collecting data for four months, the team had roughly 3 million tweets to work with. 

“We pulled the tweets based on certain hashtags provided by our in-house political scientist.”

But, as Rajamohan explains, this approach has some drawbacks. “A particular hashtag can be used by people from widely varying beliefs and backgrounds, so that’s not necessarily going to tell you that they belong to a particular group or they have a certain ideology.”

For example, say you’re trying to figure out how groups of people feel about the Black Lives Matter movement. You can’t simply assume anyone tweeting out the #BlackLivesMatter hashtag is a sympathizer to the cause, as members of white supremacist groups might also use this hashtag in a derogatory context.

This kind of ambiguous information is called dirty data, and it can be a big problem in machine learning. It can prevent scientists from actualizing any real analysis of a given dataset, and it is the most common issue facing data science workers. 

For this project, Rajamohan decided to move to a weakly supervised form of machine training to understand intent. Contextual embeddings helped mitigate noise in the data by guiding a human researcher to the incorrect records on the plots that were generated from the neural network. 

Once they had cleaner data, Rajamohan and his colleagues were able to visualize these belief structures. Although they experimented with various visualization techniques such as t-SNE, Isomap, and PCA, multidimensional scaling (MDS) turned out to be the most efficient. 

This model places liberal ideologies on the bottom left, while conservative opinions are placed on the top right. Although other techniques such as t-SNE are able to provide a more effective separation of data, MDS is able to better identify incorrect labels in the corpus.

Quantifying an opinion

To make this whole process simpler, Rajamohan focused less on specific political ideologies in favor of plotting a person’s political affiliation based on their relationship to an important public figure. For instance, your opinion of Elizabeth Warren or Donald Trump reveals a lot about your own beliefs. 

“In an ideal world, I would have a tool like this before voting.” says Rajamohan.

I would take all of the beliefs and opinions a politician ever expressed and project it on a screen. I would then take my own beliefs and opinions and put it on the screen and look who I’m closest to.

While this tool has a long way to go before it becomes something the public can rely on to pick a candidate, simply pursuing this endeavor keeps Rajamohan interested. 

“Being able to understand intent is hard,” said Rajamohan. “You have an entity, and it’s easy to say someone feels positively or negatively about something, but how do you quantify or extract someone’s intent? That is a really ill-defined concept, so if we can use deep learning or AI to extract them – I think that’s a pretty neat concept to explore.”

Read more:

• What presidential speech reveals
• Mining the news for data

This article was originally published on ScienceNode.org. Read the original article.

The post Quantifying opinion appeared first on PEARC20 - Catch the Wave.