Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:

 

Building trustworthy big data algorithms

30.01.2015

New algorithm can separate unstructured text into topics with high accuracy and reproducibility

Much of our reams of data sit in large databases of unstructured text. Finding insights among emails, text documents, and websites is extremely difficult unless we can search, characterize, and classify their text data in a meaningful way.

One of the leading big data algorithms for finding related topics within unstructured text (an area called topic modeling) is latent Dirichlet allocation (LDA). But when Northwestern University professor Luis Amaral set out to test LDA, he found that it was neither as accurate nor reproducible as a leading topic modeling algorithm should be.

Using his network analysis background, Amaral, professor of chemical and biological engineering in Northwestern's McCormick School of Engineering and Applied Science, developed a new topic modeling algorithm that has shown very high accuracy and reproducibility during tests. His results, published with co-author Konrad Kording, associate professor of physical medicine and rehabilitation, physiology, and applied mathematics at Northwestern, were published Jan. 29 in Physical Review X.

Topic modeling algorithms take unstructured text and find a set of topics that can be used to describe each document in the set. They are the workhorses of big data science, used as the foundation for recommendation systems, spam filtering, and digital image processing. The LDA topic modeling algorithm was developed in 2003 and has been widely used for academic research and for commercial applications, like search engines.

When Amaral explored how LDA worked, he found that the algorithm produced different results each time for the same set of data, and it often did so inaccurately. Amaral and his group tested LDA by running it on documents they created that were written in English, French, Spanish, and other languages. By doing this, they were able to prevent text overlap among documents.

"In this simple case, the algorithm should be able to perform at 100 percent accuracy and reproducibility," he said. But when LDA was used, it separated these documents into similar groups with only 90 percent accuracy and 80 percent reproducibility. "While these numbers may appear to be good, they are actually very poor, since they are for an exceedingly easy case," Amaral said.

To create a better algorithm, Amaral took a network approach. The result, called TopicMapping, begins by preprocessing data to replace words with their stem (so "star" and "stars" would be considered the same word). It then builds a network of connecting words and identifies a "community" of related words (just as one could look for communities of people in Facebook). The words within a given community define a topic.

The algorithm was able to perfectly separate the documents according to language and was able to reproduce its results. It also had high accuracy and reproducibility when separating 23,000 scientific papers and 1.2 million Wikipedia articles by topic.

These results show the need for more testing of big data algorithms and more research into making them more accurate and reproducible, Amaral said.

"Companies that make products must show that their products work," he said. "They must be certified. There is no such case for algorithms. We have a lot of uninformed consumers of big data algorithms that are using tools that haven't been tested for reproducibility and accuracy."

Megan Fellman | EurekAlert!

More articles from Information Technology:

nachricht Cutting edge research for the industries of tomorrow – DFKI and NICT expand cooperation
21.03.2017 | Deutsches Forschungszentrum für Künstliche Intelligenz GmbH, DFKI

nachricht Molecular motor-powered biocomputers
20.03.2017 | Technische Universität Dresden

All articles from Information Technology >>>

The most recent press releases about innovation >>>

Die letzten 5 Focus-News des innovations-reports im Überblick:

Im Focus: Giant Magnetic Fields in the Universe

Astronomers from Bonn and Tautenburg in Thuringia (Germany) used the 100-m radio telescope at Effelsberg to observe several galaxy clusters. At the edges of these large accumulations of dark matter, stellar systems (galaxies), hot gas, and charged particles, they found magnetic fields that are exceptionally ordered over distances of many million light years. This makes them the most extended magnetic fields in the universe known so far.

The results will be published on March 22 in the journal „Astronomy & Astrophysics“.

Galaxy clusters are the largest gravitationally bound structures in the universe. With a typical extent of about 10 million light years, i.e. 100 times the...

Im Focus: Tracing down linear ubiquitination

Researchers at the Goethe University Frankfurt, together with partners from the University of Tübingen in Germany and Queen Mary University as well as Francis Crick Institute from London (UK) have developed a novel technology to decipher the secret ubiquitin code.

Ubiquitin is a small protein that can be linked to other cellular proteins, thereby controlling and modulating their functions. The attachment occurs in many...

Im Focus: Perovskite edges can be tuned for optoelectronic performance

Layered 2D material improves efficiency for solar cells and LEDs

In the eternal search for next generation high-efficiency solar cells and LEDs, scientists at Los Alamos National Laboratory and their partners are creating...

Im Focus: Polymer-coated silicon nanosheets as alternative to graphene: A perfect team for nanoelectronics

Silicon nanosheets are thin, two-dimensional layers with exceptional optoelectronic properties very similar to those of graphene. Albeit, the nanosheets are less stable. Now researchers at the Technical University of Munich (TUM) have, for the first time ever, produced a composite material combining silicon nanosheets and a polymer that is both UV-resistant and easy to process. This brings the scientists a significant step closer to industrial applications like flexible displays and photosensors.

Silicon nanosheets are thin, two-dimensional layers with exceptional optoelectronic properties very similar to those of graphene. Albeit, the nanosheets are...

Im Focus: Researchers Imitate Molecular Crowding in Cells

Enzymes behave differently in a test tube compared with the molecular scrum of a living cell. Chemists from the University of Basel have now been able to simulate these confined natural conditions in artificial vesicles for the first time. As reported in the academic journal Small, the results are offering better insight into the development of nanoreactors and artificial organelles.

Enzymes behave differently in a test tube compared with the molecular scrum of a living cell. Chemists from the University of Basel have now been able to...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

Event News

International Land Use Symposium ILUS 2017: Call for Abstracts and Registration open

20.03.2017 | Event News

CONNECT 2017: International congress on connective tissue

14.03.2017 | Event News

ICTM Conference: Turbine Construction between Big Data and Additive Manufacturing

07.03.2017 | Event News

 
Latest News

When Air is in Short Supply - Shedding light on plant stress reactions when oxygen runs short

23.03.2017 | Life Sciences

Researchers use light to remotely control curvature of plastics

23.03.2017 | Power and Electrical Engineering

Sea ice extent sinks to record lows at both poles

23.03.2017 | Earth Sciences

VideoLinks
B2B-VideoLinks
More VideoLinks >>>