Algorithmia Blog - Deploying AI at scale

DubHacks Spotlight: intuiti0n Helps Find Seminal Research Papers in Any Field

image

Algorithmia was on-hand at the second-annual DubHacks hackathon last month, the largest collegiate hackathon in the Pacific Northwest. Over 600 student developers and designers flocked to the University of Washington in Seattle campus to form teams, build projects, and create solutions to real-world problems.

intuiti0n wanted to make the literature review process easier by building a service that finds important research papers across all fields of study. The team was comprised of Nirawit Jittipairoj, Alex Thompson, and Bryant Wong.

We spoke to Bryant Wong from the team, a senior at the University of Washington with a triple major (!) in mathematics, statistics, and computer science, about their intuiti0n hack.

What was the problem you were trying to solve?

“Two of the members of our team have been involved with academic research, which has the goal of trying to push the limits of human knowledge. However, in order to push the limits of human knowledge, you need know exactly what is in that field, which you do with a literature review. However, literature reviews are kind of a Catch-22 – you need to read the most important papers in a field, but because you don’t know what’s in the field, you don’t know what papers to read. As a result, literature reviews are often spent just hunting for papers that appear relevant, and then discarding most of them as they are often only tangentially related to your field. This makes the whole process tedious and extremely inefficient.”

How did you solve this problem?

“We devised an app that centered around extracting data from papers, and used them to generate topics to make targeted searches to find (other) papers. We were taking the abstract and title from a paper, running an NLP algorithm called Latent Dirichlet Analysis (LDA) on it to generate topics, then run those topics through Google Scholar, parsing the results with Beautiful Soup. The user could set a threshold for the number of papers they would like returned so that the algorithm does not run indefinitely. Our heuristic for judging the importance of a paper was not so good, as we used the number of papers that had cited this paper. Obviously this is not a good metric as there are many irrelevant papers that are cited, but we did not have a better concrete heuristic to judge by.”

How did you utilize Algorithmia in your project?

“We used Algorithmia as the backbone for our machine learning and topic generation, as we ran our data through one of the LDA algorithms available on Algorithmia to generate topics. This provided several advantages for us over implementing the algorithm ourselves: 

1) not having to implement a complicated algorithm

2) not having a powerful enough server to run the algorithm (as our local machines were not particularly powerful)

3) simple integration in our Python scripts. 

This was a no-brainer decision and allowed us to have a half-functioning product by the end of DubHacks.”

DubHacks Spotlight: BSO’Meter Fact-Checks the Politicians

image

Algorithmia was on-hand at the second-annual DubHacks hackathon last month, the largest collegiate hackathon in the Pacific Northwest. Over 600 student developers and designers flocked to the University of Washington in Seattle campus to form teams, build projects, and create solutions to real-world problems.

The winner of the Best Use of the Algorithmia Platform was BSO’Meter, an iOS app by Rosie Zou, Jules Mazur, Daniel Tran, Kim Lister, Shaheen Sharifian that used Algorithmia to analyze statements made by politicians for factual correctness. We spoke with Rosie Zou about how their hack came together, inspiration, and what they’re planning to do next.

What was your team’s goal heading into DubHacks?

“Our main goal was really to just make something cool, learn, and have fun. Winning would be great, but to us it was completely optional. We came up with BSO’Meter because of the elections going on both in the U.S. and in Canada, and wanted to make an app that tells the user how much of a political statement is completely BS.

“At that time, we didn’t really plan out which specific frameworks or APIs we were going to use, but we did a lot of research on the necessary work for both frontend and backend, and we knew that we would, at the very least, require some sort of ‘smart’ text analysis.”

image

How did you utilize Algorithmia in BSO’Meter?

“Having worked with many APIs and libraries before, our biggest concern for the backend is that the API might be hard to integrate, or that the API and the app would require different versions of a language. These didn’t prove to be a problem at all when we used Algorithmia.

“The Python Client was very easy to install, and it was my first time calling an API using only five lines of code. We also loved how the output file was a Python string instead of the usual JSON files – no parsing, yay! Shoutouts to the simplicity and conciseness of Algorithmia’s APIs!”

What algorithms did your team use? 

“We used four algorithms: Extract Text, Summarizer, Sentence Detection, and Sentiment Analysis. We wired our frontend and backend together with a web server. The user inputs a URL, we then use Algorithmia’s APIs on the backend to extract the text from the webpage, summarize the text, break down the summary into sentences, and assign each sentence with a sentiment score of 0 to 4 – 0 being very negative and 4 being very positive.

“We then take the average sentiment score of all sentences and use that value along with a Bayesian classification model that we developed, in order to analyze the text more accurately.

“We built the frontend in Xcode, using Swift 2.0, the backend programming was done in Python, and incorporated Algorithmia’s APIs. Our server was built on Tornado.”

What’s next for BSO’Meter?

“BSO’Meter is still largely a work in progress. We were very excited to have come up with a working demo during the hackathon, and we decided to continue the project afterwards. A lot of the features that we want to add to BSO’Meter would be made much easier by using Algorithmia’s APIs, including OCR, speech-to-text, and improvements on our Bayesian classification model.”

Learn More about BSO’Meter:

GeekWire Selects Algorithmia as One of Seattle’s Top 10 Startups

image

We’re honored to be included on this year’s GeekWire Seattle 10. This prestigious list showcases the 10 most promising startups in the Seattle area with world-changing business ideas.

Algorithmia was selected by a panel of judges, which included Geoff Entress (Pioneer Square Labs), Rebecca Lovell (City of Seattle), Julie Sandler (Madrona Venture Group), Mukund Mohan (Microsoft Ventures), and Leonard Garfield (MOHAI).

What they said about Algorithmia:

Quick take: It doesn’t get much geekier than this. Diego Oppenheimer and his team of computer scientists are creating a marketplace for algorithms.

The idea? Spark more algorithms by making them easier for developers to find and use.

“Our goal since day one is to unlock the algorithmic knowledge of the world and make it accessible to anyone, anywhere,” said Oppenheimer, a former Microsoft program manager who met his co-founder, Kenny Daniel, when they were students at Carnegie Mellon.

We’re now tasked with translating our business concept onto a giant, six-foot by six-foot cocktail napkin, which will be unveiled at the GeekWire Gala on Dec. 2nd at MOHAI. Get your tickets here.

About Algorithmia:

Algorithmia enables developers to create tomorrow’s smart applications today. This first-of-its-kind marketplace for algorithms unlocks the building blocks of human intelligence, providing access to world class scientific research and artificial intelligence in five lines of code or less.

Developers can now easily recognize patterns in data, extract visual knowledge, understand audio, classify unstructured data, derive meaning from language, and so much more. Algorithmia is the largest marketplace for algorithms in the world, with more than 14,000 developers leveraging 1,600+ algorithms.

“Data is inherently dumb,” Peter Sondergaard said, senior vice president at Gartner Research. “Data alone is not going to be the catalyst for the next wave of IT-driven innovation. The next digital gold rush will be focused on how you do something with data, not just what you do with it. This is the promise of the algorithm economy.”

We couldn’t agree more.

Five Algorithms Every Web Developer Can Use and Understand [Free eBook]

 

imageThe world of algorithms is as endless as it is fascinating. Working as a programmer encourages you to always pick up new tools and bring them into your applications. Our free eBook, Five Algorithms Every Web Developer Can Use and Understand by Sheldon Kreger, teaches you how to harness the power of algorithms so you can make every app a smart app.Each of the five chapters feature an algorithm available in the Algorithmia API, designed to help developers with limited background in mathematics gain access to these amazing utilities. In this short primer, we cover PageRank, Language Detection, Nudity Detection, Sentiment Analysis, and TF-IDF, and how you could implement it today.

Now you can make prototypes and iterate on your products quicker than ever. Get started making algorithms work for you so you can save time and energy.

Get your free eBook here