Sony Pixel Power calrec Sony

Pre- Vs. Post-Claification For Records Metadata by Juerg Meier

18/08/2016

I recently watched a demo of the IBM Watson natural language processing (NLP) tool that showed how it was used by police for criminal investigations at a Records and Information Management conference. I was struck by the fact that this fascinating tool may have led some Records and Information Managers in the audience to think that this was the new, disruptive way to manage records.

CAN YOU RUN A RECORDS AND INFORMATION MANAGEMENT PROGRAM ON POST-CLASSIFICATION AND MACHINE LEARNING? IBM Watson can be looked at as a post-classification tool, representing a whole group of NLP tools often marketed under the Big Data umbrella. Post-classification tools use algorithms to produce classification for an information asset after the asset is created or stored. In fact, every major supplier and the open source community offers similar tools. This can even seem overwhelming for those in the eDiscovery space.

The demo was really impressive. It was almost as if Watson went through the test documents by magic- thereby identifying people, organizations, places, phone numbers and frequently used terms. A click on one of the filtered terms lists its occurrences across various documents. The tool also has the ability to produce graphics that connect interrelated terms visually. This is, of course, quite a departure from the rather minimalistic user interfaces typically found in electronic records management systems (ERMS).

What is attractive about potentially using such an analytics tool for Records and Information Management is its ability to reduce the complexity of information management processes, in particular, capturing metadata. It could:

save us from lengthy discussions with information asset creators to get them to provide the right metadata and how and in what format its delivery should take place

eliminate the need to design metadata structures for document types, simplifying forms management and the optical character recognition process (OCR) during scanning

allow users to search for criteria originally not available for lookup

provide the ability to search for important emails in the email archive or unstructured documents.

No doubt, adopting such a tool has the potential to appear to be a silver bullet for Records and Information Managers.

However, two things should be kept in mind: with a tool like Watson, you (a) buy into algorithms and (b) require these algorithms to build the structure that has not been created and provided upfront, i.e. during an on-boarding analysis processes. Or to summarize the two issues: what sort of structure is actually used or produced by such algorithms?

NLP and text mining algorithms (with impressive names like Latent Semantic Indexing or Na ve Bayes) work on a mathematical-statistical basis, building trees based on the frequency and proximity of terms in a given document or set of documents. Typically, they don't work with pre-existing ontologies, and they don't really understand what they recognize. The algorithms are able to identify amounts in documents, but what sort of amounts are they? This is left to human review to sort out, but at least these tools can provide us hints.

PRE-CLASSIFICATION IS STILL THE WAY TO GO FOR RECORDS AND INFORMATION MANAGEMENT The classification structure for Watson is determined by its algorithms, whose outcomes are somehow unpredictable. Tools like Watson are widespread in the forensics and e-discovery communities, as these domains are often interested in unknown bits of information in datasets. But for Records and Information Management usage, this approach is simply not good enough. Precision and recall seem too arbitrary that they could truly satisfy the findability requirement stipulated in ARMA's General Record Keeping Principles, for example.

For simplicity, I am defining a record as something that it is created by a business process. Consequently, as much as business processes are defined and executed in a controlled environment, properties found in records and their metadata are also well known, and their possible values are actually restricted. Here are some of those properties:

client ID

transaction number

transaction type

privacy level

It is fairly intuitive what the metadata terms above mean. The size of their value sets (i.e. possible values) may differ dramatically, from a handful (privacy classification) to perhaps billions (transaction numbers) but both represent restricted value sets and not free, unstructured text. There is semantic behind these properties. Additionally, client IDs and transaction numbers may overlap in terms of format and value, creating serious problems for post-classification algorithms.

Pre-classification, or classifying information before creating or storing it, is clearly still the way to go for Records and Information Management professionals. Declaring the semantics of each required metadata property that describes a record and promotes finding it, and having the business process owner and the producing application to supply the correct values, remains an indispensable activity even in times of machine learning .

That said, I would not encourage you to dismiss of NLP or text mining. These tools can be very helpful if you need to classify, say, millions of office documents on shared drives or Sharepoints. But make sure it is you, the information professional, who can supply the terms, taxonomies, ontologies and document types of the knowledge domain to the analytics tool so the classification does not become arbitrary. It's all about creating well-understood, intended structure.
LINK: http://blogs.ironmountain.com/2016/service-lines/information-managemen...
See more stories from ironmountain

Most recent headlines

26/12/2024

Cheers to 2024: GeForce NOW Recaps Year of Ultimate Cloud Gaming

This GFN Thursday wraps up another incredible year for cloud gaming. Take a look back at the top games and new features that made 2024 a standout for GeForce NO...

24/12/2024

PARTICIPATE AT SERIES MANIA FORUM 2025

The National Film and Video Foundation (NFVF) is calling for applications from South African film and television filmmakers to be part of the NFVF's delegat...

24/12/2024

FCC Fines Paramount Global $244,952 for Emergency Alert Violations

WASHINGTON, D.C. The Federal Communications Commission Enforcement Bureau said Paramount Global is being fined $244,952 for violations of emergency alerting rul...

24/12/2024

Streamer Carnegie Hall+ Features Holiday Programming and Music

NEW YORK Carnegie Hall's video-streaming channel, Carnegie Hall+, said it will celebrate the holiday season by offering a wide selection of holiday-themed o...

24/12/2024

PlayersTV Acquires Cloud Media Center

LOS ANGELES PlayersTV, an athlete and fan-owned media company, has announced the acquisition of Cloud Media Center, an AI-driven sports adtech and media distrib...

24/12/2024

The Best Playlists of 2024

The Best Playlists of 2024 The top playlists we created in 2024, from dad rock to dembow. By Tara Bellucci December 23, 2024 Image by Kelly Davidson Tak...

24/12/2024

From Generative to Agentic AI, Wrapping the Year's AI Advancements

Editor's note: This post is part of the AI Decoded series, which demystifies AI by making the technology more accessible, and showcases new hardware, softwa...

23/12/2024

Broadcast and the IT industry: an inevitable evolution?

At IBC2024, Grass Valley CTO Ian Fletcher told attendees at GV Forum that broadcast is now an IT industry. During our discussions at the show, TVBEurope heard v...

23/12/2024

Cracking creation: Fun facts from Wallace & Gromit: Vengeance Most Fowl

According to co-director Nick Park, the production team embraced technology to help create the iconic duos latest adventure By Jenny Priestley Published: Dec...

23/12/2024

Mapping the great wave: how Lux Aeterna produced data-centric visuals for Tsunami: Race Against Time

VFX house Lux Aeterna used wave height data from the National Oceanic & Atmosphe...

23/12/2024

DAZN acquires Australia's Foxtel in $2.2 billion deal

We are committed to supporting and investing in Foxtel's television and streaming services, across both sports and entertainment, using our world-leading te...

23/12/2024

Looking back at 2024: the industry trends that stood out

From AI to IP, the cloud to virtual production, key industry executives take a look back at some of the biggest trends that impacted the media and entertainment...

23/12/2024

BOOST GRAPHICS THE SPECIALIST INTERNATIONAL GRAPHICS SUBS...

Boost Graphics, the specialist international graphics and virtual production subsidiary of EMG / Gravity Media, the leading force in production and content & me...

23/12/2024

LucidLink Earns TPN Gold Certification to Advance Secure...

LucidLink, the leading storage collaboration platform revolutionizing how global teams work, proudly announces its achievement of the prestigious Trusted Partne...

23/12/2024

Mediagenix Welcomes Bruno Langlais as Business Developmen...

Mediagenix, a leader in software solutions for content strategy, content value management, and content scheduling, announces the appointment of Bruno Langlais a...

23/12/2024

NextGen TV Live Spanish Captions Debut on PMVG Test Bed S...

WCTEPublic Media Venture Group (PMVG) has announced that it is now providing real-time translation of closed captioning from English to Spanish on PMVG's Ne...

23/12/2024

Deltatre Appoints Charlie Mitchell to Head Up Sports in t...

Deltatre, the tech company behind the media and sporting moments that matter, has appointed Charlie Mitchell as Head of Sports for the Americas. Charlie will sp...

23/12/2024

Media Excel Welcomes Industry Veteran Matthew Goldman to...

Media Excel, a global leader in real-time video solutions, proudly announces the appointment of Matthew Goldman to its Technical Advisory Board. A distinguished...

23/12/2024

Disguise Nikon and MRMC bring Studio Extreme immersive ac...

Disguise the company behind the virtual production technology used on commercials for Apple Music and Lenovo, as well as feature film Daddio starring Sean Pen...

23/12/2024

Moments Lab and Bitcentral Partner for AI-Powered Content...

Leading AI and video search company Moments Lab is pleased to announce its integration with Bitcentral. The integration enables Bitcentral Oasis MAM users to en...

23/12/2024

ABC Commercial Partners With Amagi to Launch Suite of FAS...

Amagi, the global leader in cloud-based SaaS technology for broadcast and connected TV (CTV), today announced that ABC Commercial has partnered with Amagi to la...

23/12/2024

Digital Alert Systems Vice President of Global and Govern...

Digital Alert Systems, the global leader in emergency communications solutions for media providers, today announced that Ed Czarnecki, the company's vice pr...

23/12/2024

New Matthews Multipurpose Adapter for Moving Lights

Matthews Studio Equipment, known for the heftiest hardware, has a new solution to simplify mounting live production moving lights to standard grip equipment. Th...

23/12/2024

Matthews Studio Equipment Debuts RoadBags

Matthews Studio Equipment expands its trusted Road-line with the launch of RoadBags, durable fillable sandbags available in three sizes. Whether in the studio o...

23/12/2024

Sport Lisboa e Benfica Enhances Stadium Communications wi...

Sport Lisboa e Benfica, one of Portugal's most prestigious football clubs, has partnered with Clear-Com to upgrade the communications system at the Est dio...

23/12/2024

Black Box at Hamburg Open 2025

At stand B6.734, Black Box will showcase its Emerald KVM-over-IP solution, which enables smarter studio control with secure remote access from anywhere, along...

23/12/2024

OOONA Partners with Audio Description Associates

OOONA, a leading provider of professional management and production tools for the media localization industry, announced today a partnership with Audio Descript...

23/12/2024

Dunk The Halls: ESPN Refines Animated Altcast Tech and Ops with a Helping Hand From Mickey and Minnie

Dunk The Halls: ESPN Refines Animated Altcast Tech and Ops with a Helping Hand F...

23/12/2024

Leading Through Change: In Conversation with Michal Masset, Chief People Officer

With the holiday season in full swing, we are delighted to bring you a special digital event, Leading Through Change with Technicolor Group's Chief People O...

23/12/2024

Netflix Kicks Off NFL Christmas Games: Behind the Scenes With the Streaming Giant and Its Production Partners

Netflix Kicks Off NFL Christmas Games: Behind the Scenes With the Streaming Gian...

23/12/2024

ESPN's Tina Thornton on Producing The Simpsons Funday Football, Upcoming Dunk the Halls Alternative Broadcast on Christmas Day

ESPN's Tina Thornton on Producing The Simpsons Funday Football, Upcoming Dun...

23/12/2024

Dunk The Halls: ESPN Refine Animated Altcast Tech and Ops with a Helping Hand From Mickey and Minnie

Dunk The Halls: ESPN Refine Animated Altcast Tech and Ops with a Helping Hand Fr...

23/12/2024

NFL Christmas Gameday Live Comes to Netflix With Blimps, Hot Cocoa Trucks and Two Superstar Performances

Back to All News NFL Christmas Gameday Live Comes to Netflix With Blimps, Hot C...

22/12/2024

News Corp Announces Agreement to Sell Foxtel to DAZN for Enterprise Value of A$3.4 Billion

News Corp Announces Agreement to Sell Foxtel to DAZN for Enterprise Value of A$3...

22/12/2024

Netflix Showcases Global Anime Hits and New Releases at Jump Festa 2025

Back to All News Netflix Showcases Global Anime Hits and New Releases at Jump Festa 2025 Entertainment 22 December 2024 GlobalJapan Link copied to clipboar...

21/12/2024

L3Harris Thrusters Position NASA Probe for Closest Approaches to the Sun

Artist's concept of the Parker Solar Probe spacecraft approaching the sun. Credit: NASA/Johns Hopkins APL...

21/12/2024

Dallas Mavericks Roll Out New Streaming Platform

DALLAS and NEW YORK The NBA's Dallas Mavericks, working with Endeavor Streaming, Softtek and the NBA, have launched an official streaming platform for MavsT...

21/12/2024

Former FCC Chair Expresses Concern' Over Musk's Influence

As tech billionaire Elon Musk takes an increasingly high-profile policy role in the incoming Trump administration, a former Federal Communications Commission ch...

21/12/2024

Gray Media Renews Comscore Measurement Deal

RESTON, Va. Comscore has announced that it has renewed and expanded its measurement deal with Gray Media....

21/12/2024

Sinclair, Gray Media to Broadcast Columbus Blue Jackets NHL Games

The Columbus Blue Jackets, Sinclair and FanDuel Sports Network have signed a deal that will allow Sinclair and Gray Media stations in select markets to simulcas...

21/12/2024

Our Favorite Songs of 2024

Our Favorite Songs of 2024 Explore a playlist featuring some of the top songs of the year, as picked by members of the Berklee community. By Tara Bellucci De...

21/12/2024

Berklee Wrapped 2024: Our Top News and Stories

Berklee Wrapped 2024: Our Top News and Stories Take a look at some of our best stories of the year, including announcing our next president, hosting Andr 300...

21/12/2024

Alumna Allison de Groot Awarded 2024 Steve Martin Banjo Prize

Alumna Allison de Groot Awarded 2024 Steve Martin Banjo Prize De Groot, a former student of the American Roots Music Program, was recognized for her unique so...

20/12/2024

Thinking of Launching a Podcast? Let Our New Guide Show You How

Podcasting has become one of the most popular ways to tell stories and connect with audiences, but getting started can be intimidating, especially when it comes...

20/12/2024

2025 Sundance Film Festival Reveals 92 Projects for Feature Film and Episodic Programs

Top L-R: The Legend of Ochi, Rabbit Trap, East of Wall, Seeds Center Row L-R: Re...

20/12/2024

Spotify Presents the First-Ever Billions Club Live Show With The Weeknd

For any song to rack up billions of streams is an impressive accomplishment, but being a part of Spotify's Billions Club is something The Weeknd knows quite...

20/12/2024

Curl Up Under the Mistletoe With These Holiday Romance Audiobooks

It's the most wonderful time of the year, but if you seek an escape, pop in your headphones and enjoy the soothing sounds of a story. And this season, a rom...

20/12/2024

Revisit 2024 With Some of Your Favorite Podcasts From The Ringer

As the year draws to a close, Spotify's The Ringer is celebrating the best of 2024 with an exciting lineup of retrospective podcast episodes. This December,...

20/12/2024

HPA Award Delivered To New Zealand!

HPA Award Committee co-founder Carolyn Giardina was in New Zealand recently and had the opportunity present the Outstanding Visual Effects - Live Action Feature...