Each unqiue user visit is an opportunity to learn about customer communication preferences.  Each unique customer will have a unique experience with a single product sales message.  By personalizing product messages and distributing them to users based on probabilities of message resonance, page engagmenet and conversion, product marketers can deliver a substantially improved customer experience to each unique user.

First to Launch

Launch products before the container lands at your warehouse by virtually eliminating the content production bottleneck.  Test products, before purchase order, with carefully targeted messaging produced quickly and at a low cost.  Be first-to-market on new launches and respond quickly to successful competitor launches.  Sell products on a pre-order basis or with adjusted ship times.

First to Edit

Keep content fresh and updated – this is more important in online retail than any other content category.  Eliminate the mental block of having production limitations in the writing department.  Operate more freely and flexibly with product message editing and marketing agendas.  Never stop editing.  Fresh and personalized content will always win.

First to A/B Test

Create 100 unique product pages for a single SKU and test them all against each other and targeting differentiated user groups.  Test 100 unique ads with 100 unique product pages.  Create dozens of product descriptoin versions for each unique ad.  More differentiation.  More variables to test.  Better data between language and user.  Better language with NLG created specifically for product messaging.

First to Adapt

Data that explains how users behave with product communications is decision-able data, but not for humans.  Sure, you can use bits and pieces to create better message with a few segments, but your future success is tied to your ability to personalize the customer experience, not analyze it. Writesof gives product markters the power to adapt to each user, community, behavior shift, and new trend – to stay on message, delivering unique customer experiences via user-targeted product communications.

First to Adjust

Seasons change.  Promotional opportunites can be sudden.  Social media activity can throw you off guard.  New product launches can take you by surprise.  Writesof NLG adds agility and productivity to your marketing team and substantially reduces pressure on your writing department.  For writers who can accept the learning curve, both by the machine and by the human writer, our technology will virtually eliminate burdens on a departmental level, from data to distribution.

First to Differentiate

Content differentiation is non negotiable for search optimization.  All of your text content must be 100% unique, on-site and off-site.  Brands that sell thousands of unique SKUs may have thousands of unique resellers for each SKU. Writesof NLG can deliver customized product descriptions, millions of versions per SKU.  Brands can distribute each version, by country (foreign language), state, city, audience type, etc.  Differentiated content is critical – the other reasons should be obvious to a product marketer.

First to Personalize

As our NLG learns about your customer base and user traffic, it will also learn how to adapt messaging to communicate more effectively to user groups and eventually to individual users.  In our opinion, in 2020, personalized communications is a myth.  It is impossible to even begin to understand how diversified people are.  The only way to pursue personalized communications is with machine learning, driven by user communication feedback.  The only way to do this, at this time, is with onine retail, where the user is providing difinitive engagement and responses.  It is the only area of the www where enough volume of user visits and data-rich interactions exist.  There are other humanitarian areas that Writesof plans to pursue with our NLG pursuits.  At this time, online retail, is the best training ground for our systems.  Over time, as they learn how people interact on social media, with respect to products, they will acquire more knowledge in the area of social communications, which is an important area of focus on training our NLG to communicate to all types of people, with various communication objectives.

First to Compete

Organizations can start selling inventory before their competitors.  With higher quality, more enriched, and more personalized product messaging, product marketers will be stronger in all corners of the digital market, from press, to social media, to product pages.  First is always stronger, in position, in data, in agility.  The competitor that gets to the customer first, all else equal, will always win on position and visibility.  But all else is not equal – your messaging will be better than your competitors.  You can start taking market share before their launch.  You can respond to new product opportunities and competitive threats faster than the competition.

Writesof is an author-tuned NLG (natural language generation) system that uses audience data (more specifically, user profile and behavioral data) to train our systems to systematically compose messages that are more likely to influence buying decisions with specific users and user groups.  Our NLG learns from audience feedback (user engagement and behavior) with product messages.  While learning, it can create thousands, even millions of unique product sales messages, each targeting individual users, running 24/7, with limited and declining human supervision requirements.

Our technology empowers organizations to create, edit, and strategically position all product communications with first-to-market speed and user-targeted precision.  Product marketers can publish new products and edit existing products, on demand.  Their product communications can be more diversified, more enriched, and personalized for unique users.  Our systems can learn from virtually any type of user data, to include many types of “hidden” third-party data.  Each user interaction with a product message informs our system with engagement and user profile data that helps train our NLG to understand which forms and functions of a message is likely to improve engagement and conversion with specific users.

Prospective customers are activity searching for informative and helpful product information.  They want to be uniquely informed, compelled, inspired, and assured, before they decide to purchase. As a Writesof partner, you can add substantial value to your internal and third-party customer data, creating new messaging data that enables our NLG systems to compose and edit personalized product messages that speak to the individual user.

Customers are more likely to remember high quality content.  Personalized messaging will create more customer conversions.  Customers will return to sites with higher quality, more enriched, and more personalized content.   They are more likely to buy, come back to buy again, and engage after the sale.  Customers who feel connected to content are also more likely to become loyal customers and fans.  They are more likely to promote your brand and its products with reviews and in social media.  Personalized communications is the best path to customer relationship building.  A more engaged and responsive customer base is and has always been a function of customer experience, and communicating with customers in a more personalized manner is by far the most influential function of customer experience.

Our NLG systems produce narratives by learning from your audience and adapting messages to suit different customer behaviors, interests, and attitudes. Software that interprets language data is only as useful as its ability to interpret relationships between language data and user data.  User feedback, by profile and engagement dimensions, informs our NLG about how well parts of a message compels the customer to stay on the page and click the buy button.

A single message delivered to different users will have differing communication values, as interpreted by the user.  Each word is valued by its relationship to other words on the page, with respect to user data.  Our computational lingusitics systems is capable of discovering billions of unique value correlations between the a single message and resulting audience feedback. Word relationships are not binary.  They are multivariate.  A single word on one product page has a unique relationship with all other words on the page.   A single word can have hundreds of linguistic / communicaiton properties.  A single user can also be defined by hundreds of unique properties.  Picture a multi-dimensional relationship network that evaluates connections between differing properties of users, differeing properties of their behaviors, and differeing properties of language.  Our systems are capable of detecting patterns between these multi-dimensional relationships, determining which type of language is likely to result in a particular type of behavior from a particular type of user.

Each unqiue customer is telling you how they want to be spoken to. Writesof Natural Language Generation (NLG) systems are comprised of one hundred unique NLG Personas, brand-tuned writing machines that create content by listening to users and understanding how different users prefer to engage with content.  Each Persona has a unique communication style and writing ability, restricted by factors such as vocabulary, reading level, community dialogue awareness, etc.  Before an NLG Persona is deployed to go to work for a client, it must first be tuned to write product messages in a brand’s unique voice.  Not every Persona is suitable to write content for a specific brand or to a specific audience, but each unique Persona can be cloned and modified in our communication tuning process.  This process analyzes brand inputs, for example, text and metadata from 20,000 unique product pages on a brand’s website.  First, we use a language classifier to parse and classify each page’s text and metadata to determine the exact location and purpose of each and every word.  Word location data enables our system to understand how all of the different words are used together, by relationship and proximity, on a given product page.  Once our systems has ordinally mapped all of the text by word location, it begins classifying each piece of text (words, n-grams, phrases, sentences) by its qualitative and quantitative linquistic attributes.  This enables our systems to understand what type of language is used, where it is used,  and how it is used, grammatically.  However, at this stage, our system doesn’t know how effectively the text communicates to different users and user groups.  By giving our system understanding of communication forms, functions, and objectives, it is capable of also receiving feedback, just as a human would.  Unlike a human, our system must modify its use of language to improve communications with certain users and user groups.  It is instructed to find patterns in types of language that results in increased customer engagement and conversion.

by word relationships and context relationships.  We use location and ordinal data to build out these relationships by n-grams, where n represents the numeric value of words grouped together, in a context.  Unigram – one word.  Bigram – two words. Trigram – three words. identified all of the lan  This enables our system to understand how   page, section, and communication objective,  etc.  Then our Natual Language Processing tools further classify the textso that our systems  understand the type of  Currently, Writesof’s NLG Personas are suitable for product markters who want to create and edit performance-driven product sales communications, from text ads to fully-enriched 500-word product descriptions.  Your NLG Persona must be brand-tuned to communicate with a particular house style of communication.  Product messages are then systematically composed by analyzing message engagement signals from different user types.

Our PMG system is designed to learn how unique users engage with unique messages.  Each user interacts with a product sales message in a unique manner.  If you can identify particular qualities and behaviors of the user, you can begin to build correlation valuations between language qualities and user qualities, with predictively high resonance language segmented according to user-type.  Different strokes for different folks.  PMG is an advanced science that looks at language according to its predicted value, as per information, resonance, influence, and decision.  We capture user-behavior-with-language data to better understand how changing different parts of a message results in varied outcomes with different types of users.


The Three Dimensions of PMG

  1. User – unique page visit by a person or a bot – profile and behavioral data
  2. Language – every word and phrase combination, usable by a brand.
  3. Message – language forms and functions, with user-communication objectives
  4. Engagement – unique user’s interaction with any part of a page or message
  5. Brand – word and language usage preferences and limitations – voice, style
  6. Persona – all possible language usage and vocabulary of a style-tuned NLG system

As a part of Writesof’s neural network, there

  1. e)queued by value,  segmented by user or user group.  If you  of the user, that means that you c, leaving behind a signature of behavior and profile qualities.  This system is able to identify how a specific user engages with text content  B.    Our Personalized Message Generation™ (PMG) system datawith signaling from user data (e.g. engagement, conversion metrics) to communicate to specific users or user groups.  Our computational lingusitics systems analyze the many ways that users interact and engage with content along the customer journey.  Then, our NLG systems semi-autonomously produce and edit messages, with each unique message being adpated to communicate to specific users and user groups.

Writesof’s Personalized Message Generation™ (PMG) technology is a type of dynamic Natural Language Generation (NLG) technology that creates user-tailored product messages that are systematically composed by probabalistic ability to to result in increased engagement and response for a particular user or user group.  An NLG Persona is “trained” to write in a particular brand’s voice by analyzing brand-sourced text, such as website product pages, meta data, promotional emails, and reviews.  It can also be trained by analyzing external messaging sources, such as social media group (community) dialogue, compeitor messaging, and product articles.  It can learn exactly how a brand communicates with users and how users interact with brand or product-category messages.  For example, it can learn how a brand communicates to users by analyzing 20,000 product descriptions on a large e-commerce site.  As long as the brand our author-source contains, at minimum, millions of words of text, Writesof NLG Personas can use the text as a foundation for language modeling, constrained by brand voice and communication style.

The brand-tuned Persona has the ability to expand its vocabulary and language usage by probabalistically discovering similar langauge forms and communication styles from a variety of sources, including our own internal linguistics libraries, and also external sources such as competitor sites, social media, and product articles.  Our internal systems enable us to filter through language forms and classify chunks of language using hundreds of linguistic criteria.  This enables us to use human oversight in the brand tuning process.

Our systems utilize user data to influence PMG decision-making.  The system can probabalistically determine which version of a product page a user should land on.  It can analyze how unique users engage with content along the customer journey, particularly on the landing page.  It also analzes user data to determine what types of language is most likely to create resonance, engagement, and conversion at the user level.

An NLG Persona learns to write like a human by analyzing source text and classifying it by linguistic attributes such as diction, grammar, style devices, and sentence structure. With PMG technology, the machine Persona learns how a human writer describes product features, benefits, advantages, and uses to specific users and user groups.  The brand-tuned Persona can actually predict how a human writer would communicate a product sales message by subject, attributes, and topic objectives.

The Persona automates the organization of language compositions by creating adaptations of existing language models – creating and testing new product page variants and learning which types of language performs best with certain user types on a probability-performance metric basis.  The PMG system makes decisions on word choice and message mechanics by probabalistically determining which language usage is most probable to achieve the message objective – engagement and conversion metrics.  As the system analyzes thousands, or preferably hundreds of thousands of user engagement sessions, it learns how different types of users engage with different dimensions of product sales messages.  And as it analyzes more user-page interactions, it begins to improve its predictive capabilities in communicating with different types of users.

When the Persona makes good decisions, it is rewarded with additional creative and experimental freedom with language edits.  When it makes poor decisions, it is restricted to more conservative language edits, at times reverting back to baseline (benchmarked) language choices.  If a product page still performs poorly after reverting to a conservative message state, it is sent to an editor oversight queue, where human editors make adjustments to the message.  Each human-implemented edit actually makes our system smarter, as their edits are inputted into the NLG Persona’s language libraries as validated language sources.  All language sources are tracked, at all times, with our systems.  We use language data sources (by page) to find correlations in message value by source, message style, vocabulary, etc.

The PMG system is constantly analyzing how each word connects to other words, to form a message – by writing mechanics, sentence structures and grammars, word choice, communication styles, message tone, and communication objectives, etc.  Language usage (how words connect to form a message) is determined by a message’s linguistic properties and values (for example, similar use in a social media group), but more importantly, it is determined by how users engage with various aspects of a message.  The PMG probabalisitcally determines how to compose a message by probabalistically predicting which components of a message, pieced together in a certain order, will result in increased user engagement and sales conversion.

Each of our NLG Personas can create uniquely styled narratives aimed at different audience types, on a wide rage of subjects and topic objectives.  This means that one unique NLG Persona can create product descriptions for shoes, soccer balls or dog food.  Since Writesof currently offers over 100 unique NLG Personas, we can help product marketers select and test different Personas for specific product categories, and A/B test multiple Personas in a given product category.  Each NLG Persona has a unique set of writing skills and qualities.  For example, one Persona may have been trained with added influence from social media group dialogue.  Another may have been trained with restrictions to a 4th grade reading level.  Still, another may be trained to communicate with senior citizens in Texas.  As marketers improve their understanding of unique shoppers, their ability to personalize the customer experience improves.

An NLG Persona will have a particular vocabulary (ranked by usage frequency), reading-level, persuasion capability, and communication style and tone repertoire.  Unlike human writers, each Persona is capable of producing content 24 hours per day, 7 days a week, capable of generating thousands of new or versioned product descriptions every day.  It can also edit content or change content distribution decisions in near-real-time, computing live feed user engagement data with millions of respective text strings.   This enables Writesof to deliver a personalized shopping experience for each and every unique user, with near-real-time content edits and updates and user-targeted product page version-dependent redirects.

Our pseronalized messaging technology utilizes consumer behavior data signals to autonomously train each NLG Persona individually.  A Persona communicates with each user in a unique manner.  With user-personalized messages that can be delivered to a target user, in real-time, your organization can publish millions of 100% unique, goal-oriented narratives that are strategically descriptive and persuasive.  In a matter of hours, our system can launch as many as 100 brand-tuned NLG Personas, each delivering highly differentiated product messaging, as many as dozens of product page versions for each SKU.

Each Persona is trained to model a human’s writing style, learning about what types of language describes certain products from published product descriptions, ads, articles, and social media.  Our systems analyzes language by word-string relationships and word locations within content.  It analyzes language usage on a probabalisitc determination model by examining word usage cohesion by frequency.  by word cohesion, with respect to subject attributes and communication objectives, by each language string in a page (document) section.  It tends to be intelligent enough to ignore language strings that are written by different authors unless they happen to work well together.  Thus, our technology can actually identify and predict language mechanics and form from two distinct authors.  It does this by analyzing linguistic parameters, with respect to product attributes and benefits, with respect to the communication objective, which is always determined by audience/user characteristics.  The user is the foundation for which the NLG Persona makes decisions in the language generation process.

Writesof is an author-tuned NLG System that uses audience data to make systematic language decisions.  Audience data is the fuel of any type of cognitive marketing automation technology.  User data makes it possible for a machine to learn how to write, tell a story, and stay on message.  With AI, our NLG can adapt to audience feedback (user engagement and behavior), creating hundreds, even thousands of unique product narratives, targeting individual users.   Like other Natural Language Generation systems, ours can run repetitive writing tasks on autopilot, empowering your organization with communications and messaging, on demand.  Publish first.  Edit first.  Adjust first.  Differentiate first – for each unique user visit.

Face it.  Your customer data is rich with insights, but putting user and audience data into action is not exactly a seamless process.  At best, it empowers your marketing team with more precise targeting capabilities, but it mainly only helps at the human-decicion level.  Most advanced marketing automation solutions have not yet been able to deliver real-time customer-facing product pages that adapt to the user’s needs.  If you are one of the few organizations that are personalizing customer experience with automation (such as display ads), you are a step ahead of the competition.  But the landing page experience is still static.  Your landing pages don’t yet match your targeting efforts and potential cusotmers bounce because they don’t feel the connection.  Meanwhile, your audience is becoming more differentiated, more picky, and a faster-moving target that never lacks in demand for content that speaks to them and informs on a personalized level.

Writesof works with both structured and unstructured data sources. We also provide partner clients with supplemental subject matter and audience-level data, including product language data from category-compeitors.  We use such data internally for system training.   Our NLP systems can learn from demographic, social, and behavioral data, which trains our system on linguistic characteristics that tend to perform well with particular users and user groups.

Prospective customers are activity searching for informative product information.  Most want to be fully informed, compelled, inspired, and assured – in differing ways – before they decide to purchase. As a Writesof partner, you can add substantial value to your internal and third-party customer data, creating personalized product messages that capture your audience’s attention.  Customers will remember high quality content.  They will buy more and they will come back for more.  They are more likely to become brand-loyal fans, promoting your brand and products on social media.  Communications has always been the best path to relationship building – this is especially true with online product communications.

Today, NLG can produce narratives that learn from your audience and adapt to different customer behaviors and interests. Software that interprets language data is only as useful as its ability to interpret language relationships to user profile and behavior data.  If not, the data is simply an indicator of language performance with a single audience.  This has very little value, or at least it will in the near future, as message personalization becomes more standard practice in online retail.

A single message delivered to different users will have differing values of linguistic properties.  Each word is valued, in relationship to other words on the page, with respect to user engagement and profile data.  In fact, each word will have a different value, depending on the user that sees (or doesn’t see) the word.  A user doesn’t have to see the word on a page for the word to have positive value.  A word’s value can be generated by a number of psychoanalytical factors.  Some words are even subliminally consumed or do not directly resonate with the user, but still add value, as a function or perceived feature of the message.  Example:  A segment of users show better engagement and conversion resonse when they view technical jargon on a page, even if they don’t read it; another segment is turned off by the technical jargon.  Both segments didn’t read every word of jargon, but one tended to respond more positively to it.

With AI, our computational lingusitics systems can easily find billions of correlations between the message and the audience. It would take a human writer years, even with a team of data scientists to process, even high-level insights generated from billions of data correlations.  Word relationships are not binary.  They are multivariate.  A single word on one product page has a relationship to a different word on a different product page, even if it’s on a different website.  Conisder the buyer’s journey, or a product category’s / substitute product’s product page, ad, social content footprint.  Now imagine putting all of this data into a multi-demensional spreadsheet, where a single word can be associated with hundreds of attribute variables, built out by different audience / user dimensions.  This technology gap can only be bridged with AI and machine learning, systems that not only interpret the lingusitc data and user data, but also takes on a personal identify of a human writer or team of writers, within brand voice language constaints.  And if your production schedule is time sensitive or market-response sensitive, a human writer would need to continuously adapt to an increasingly diversified and ever-changing audience, analyzing incoming customer data while simultaneously producing new messages that meet audience needs.