Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:


Building trustworthy big data algorithms


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 Next Generation Cryptography
20.03.2018 | Fraunhofer-Institut für Sichere Informationstechnologie SIT

nachricht TIB’s Visual Analytics Research Group to develop methods for person detection and visualisation
19.03.2018 | Technische Informationsbibliothek (TIB)

All articles from Information Technology >>>

The most recent press releases about innovation >>>

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

Im Focus: Researchers Discover New Anti-Cancer Protein

An international team of researchers has discovered a new anti-cancer protein. The protein, called LHPP, prevents the uncontrolled proliferation of cancer cells in the liver. The researchers led by Prof. Michael N. Hall from the Biozentrum, University of Basel, report in “Nature” that LHPP can also serve as a biomarker for the diagnosis and prognosis of liver cancer.

The incidence of liver cancer, also known as hepatocellular carcinoma, is steadily increasing. In the last twenty years, the number of cases has almost doubled...

Im Focus: Researchers at Fraunhofer monitor re-entry of Chinese space station Tiangong-1

In just a few weeks from now, the Chinese space station Tiangong-1 will re-enter the Earth's atmosphere where it will to a large extent burn up. It is possible that some debris will reach the Earth's surface. Tiangong-1 is orbiting the Earth uncontrolled at a speed of approx. 29,000 km/h.Currently the prognosis relating to the time of impact currently lies within a window of several days. The scientists at Fraunhofer FHR have already been monitoring Tiangong-1 for a number of weeks with their TIRA system, one of the most powerful space observation radars in the world, with a view to supporting the German Space Situational Awareness Center and the ESA with their re-entry forecasts.

Following the loss of radio contact with Tiangong-1 in 2016 and due to the low orbital height, it is now inevitable that the Chinese space station will...

Im Focus: Alliance „OLED Licht Forum“ – Key partner for OLED lighting solutions

Fraunhofer Institute for Organic Electronics, Electron Beam and Plasma Technology FEP, provider of research and development services for OLED lighting solutions, announces the founding of the “OLED Licht Forum” and presents latest OLED design and lighting solutions during light+building, from March 18th – 23rd, 2018 in Frankfurt a.M./Germany, at booth no. F91 in Hall 4.0.

They are united in their passion for OLED (organic light emitting diodes) lighting with all of its unique facets and application possibilities. Thus experts in...

Im Focus: Mars' oceans formed early, possibly aided by massive volcanic eruptions

Oceans formed before Tharsis and evolved together, shaping climate history of Mars

A new scenario seeking to explain how Mars' putative oceans came and went over the last 4 billion years implies that the oceans formed several hundred million...

Im Focus: Tiny implants for cells are functional in vivo

For the first time, an interdisciplinary team from the University of Basel has succeeded in integrating artificial organelles into the cells of live zebrafish embryos. This innovative approach using artificial organelles as cellular implants offers new potential in treating a range of diseases, as the authors report in an article published in Nature Communications.

In the cells of higher organisms, organelles such as the nucleus or mitochondria perform a range of complex functions necessary for life. In the networks of...

All Focus news of the innovation-report >>>



Industry & Economy
Event News

Virtual reality conference comes to Reutlingen

19.03.2018 | Event News

Ultrafast Wireless and Chip Design at the DATE Conference in Dresden

16.03.2018 | Event News

International Tinnitus Conference of the Tinnitus Research Initiative in Regensburg

13.03.2018 | Event News

Latest News

Modular safety concept increases flexibility in plant conversion

22.03.2018 | Trade Fair News

New interactive map shows climate change everywhere in world

22.03.2018 | Earth Sciences

New technologies and computing power to help strengthen population data

22.03.2018 | Earth Sciences

Science & Research
Overview of more VideoLinks >>>