Making Tracx

Out of The Dark Ages: The Rise of Social Media Sentiment Analysis, Part 3 – The Enlightenment

Posted by Ben Foley on Nov 13, 2014 12:57:16 PM


The Enlightenment

“The shift from scoring overall posts to scoring individual entities allows users to analyze the sentiment of multiple terms and phrases more reliably and accurately.”

The desire to measure social sentiment at a more granular level has risen rapidly within the social media industry. How do you gauge the sentiment of a long-form post, or even a Tweet conveying mixed signals? How can you group terms and phrases together to gain a greater understanding of sentiment within unique and flexibly defined categories relevant to your industry and company?

A better, more accurate scoring mechanism is needed. That mechanism is Sentity.

The Introduction of Sentity

The process of scoring, recording, and reporting sentiment on social media has been changed dramatically with the introduction of Tracx’s Sentity engine. Sentiment classification is no longer based on language cues across the entire post, as users can now define specific keywords and phrases for sentiment tracking called “entities.” With Sentity, greater accuracy and deeper analysis are gained by looking at smaller pieces of language surrounding each mention of these user-defined entities. In addition, entities can be grouped into larger categories for greater insights into key focus areas for brands.

Entities are terms representing a single person, place, or thing, about which data can be stored. Entities maintain distinct and separate existence and objective, can be classified, and have stated relationships to other entities. This shift in focus from entire pieces of content to individual entities within each post allows users to analyze the sentiment of multiple terms and phrases within a single piece of content to uncover truly actionable, focused insights.

Sentiment classification is no longer limited to just looking for cues across entire social posts, but instead efficient algorithms start the process by looking at smaller pieces of language surrounding the content, called “entities.”


For instance, in the example above, a traditional sentiment engine would see the words “wonderful” and “thanks,” and score the post as positive. In reality, the Tweet is expressing sarcasm, and actually should be scored as negative sentiment.

But More Importantly…

More importantly, by layering in the use of definable entities, and by tagging the “delayed flight” portion of the post as having a negative sentiment within a “flight status” entity, an organization can then start to gain deeper insight into more granular categories. The Sentity engine provides easy measurement into key areas of a brand, not just an overall score. The above-cited example could have contained more complex messaging, and actually could have been tagged across multiple entities based on user-defined criteria, yielding highly accurate sentiment scores directly aligned with an organization’s KPIs.

By compiling a complex sentiment score through identifying specific entities within the entire post, generalized and inaccurate classifications of expressive tone across a whole post become a thing of the past… Good riddance to vague and inaccurate methods!

Contact us below to receive a free demo of Tracx.

Read More

Topics: Analytics, White Paper, Sentity, sentiment,

Out of The Dark Ages: The Rise of Social Media Sentiment Analysis, Part 2 – The Renaissance

Posted by Ben Foley on Nov 12, 2014 4:45:00 PM



The Renaissance

"The machine-learning algorithm method of scoring sentiment was executed at the post level, meaning that each text-based piece of content was reviewed and scored overall based on language cues."

Prior to The Renaissance, sentiment analysis in social media was manual, slow, inaccurate, and limited heavily by the technology readily available in the marketplace. But things were changing rapidly…

Once the concept of sentiment analysis had been legitimized and adopted throughout the social media industry, significant strides were made to automate the scoring, recording, and reporting processes. The biggest enhancement of sentiment analysis rested on the shoulders of machine-learning algorithms.

The Rise of Machine-Learning

By 2013-2014, algorithms being utilized by major SMMS platforms yielded about 70% accuracy when it came to identifying posts as positive, negative, or neutral. If an organization wanted to increase the accuracy beyond that, a skilled representative would train the system by sorting through a significant number of social posts, and manually scoring them until the algorithm had enough data to refine its definition of positive, negative, or neutral sentiment.

The new wave of machine-learning was significant for the evolution of sentiment analysis, as algorithm-based sentiment scoring only grew more accurate over time depending on the number of posts scored. Analysis at the post level meant that each piece of content received an overall score. While a post may have been comprised of both positive and negative expressions, only one definitive social media sentiment score would be applied, thus limiting an organization’s understanding of consumers’ true perception of their brand.

Limitations: An Example

In the following example Tweet, we look at the limitations that early machine learning surfaced.


The limitations of this generation of sentiment analysis meant that mass generalizations of the true sentiment driving the pieces of content were unavoidable, as there were only three levels of scoring – positive,
negative, and neutral. As shown in the example above, social posts can express sarcastic tones that would be misinterpreted by sentiment tracking engines. A traditional system would see the words “wonderful” and “thanks,” and ultimately score this post as positive, when in reality it's actually expressing a very negative experience.

“Brands demanded greater granularity and segmentation of sentiment data.”

Brands Needed More Control

In addition to the language limitations, brands needed a way to categorize sentiment across different categories that were important and unique to each organization. The majority of platforms on the market only provided basic machine-learning sentiment coupled with limited filtering functionality. Brands demanded greater granularity and segmentation of sentiment data. They needed a structured framework to address sentiment in key areas that each brand needed to measure. For instance, a CPG brand would benefit from looking at packaging, taste, ingredients and other categories, while an automotive company would have far different categories like comfort, handling, service, and others. The “general” sentiment score did not tell an accurate story, unless that score could be further broken down.

In addition, many of these tools were standalone offerings that required jumping between different platforms and using disparate data sets. While this was a partial solution, sentiment outside of context was inaccurate.

But these hurdles would soon be obsolete…

Contact us below to receive a free demo of Tracx.

Read More

Topics: White Paper, Sentity

Out of The Dark Ages: The Rise of Social Media Sentiment Analysis, Part 1 – The Dark Ages

Posted by Ben Foley on Nov 11, 2014 1:59:00 PM

OutofTheDarkAges blogpost header resized 600

Over the past 5 years, sentiment analysis has become an increasingly integral part of social media management for enterprises of all sizes. No matter what industry or vertical an organization may be in, it is imperative to gain a secure hold on how people and consumers are receiving company messaging and product information. As social media continues to prove itself as an unbiased and convenient forum for individuals to express their emotions, sentiment analysis is the key to understanding how various demographics feel about a certain product, brand, or experience.

In this three-part blog series, we’ll take a look at the history of sentiment analysis in social media, a period that we have deemed The Dark Ages. Then we’ll move on to the current use of sentiment analysis, The Renaissance. Finally we’ll give a preview of the future social sentiment, The Enlightenment.

The Dark Ages

"In the early days of organizations using social media to push business further, every aspect of capturing and implementing sentiment scores into corporate initiatives was a very manual and solicited process."


In The Beginning

During the past 2 years, the social media industry has experienced incredible growth in scoring and functionalizing sentiment analysis. Sentiment can be defined as a view or attitude towards a situation or event, and refers to people’s feelings and opinions on a given subject. That being said, measuring and quantifying sentiment surrounding an industry or brand is essential for an organization to gain a secure hold on how people are truly receiving their messaging, products, or their overall voice.

Beyond The Obvious 

By looking at obvious numbers such as the amount of company page likes, number of followers, and volume of interactions received on owned media content, brand managers used to compare their social impact to the numbers of their competitors. But the industry would later learn that high-level statistics such as amounts of followers quickly become irrelevant and misrepresentative, as someone can follow a company on social media but never show any further interest in what that company is saying or doing.

Beyond the inaccuracy of only looking at non-descript statistics, during the corporate social media Dark Ages, the approach to measuring sentiment was one plagued by the use of solicitation. Brands would openly and directly ask consumers and people with interest in an industry about their sentiment regarding brands and campaigns via surveys and focus groups. While this was useful at the time, and insights into general audience reception were gleaned, with this method comes the unavoidable obstacle of overcoming biases.

The Technology Bottleneck

Eventually, managers within the enterprise came around to recognize the importance of measuring and recording the sentiment of the individualized, consumer-produced posts surrounding their brand. This process proved to be manual and excruciating, as someone would have to physically dig through each post and tag it as having positive, negative, or neutral implications. There were no text-analysis algorithms in place that could accurately score sentiment of these individual posts, and therefore no easily obtainable and summarizing reports that could then be passed up to the C-level.

It wasn’t until later on that the process of sentiment scoring, recording, and reporting began to become more automated and streamlined…and social media sentiment analysis emerged from The Dark Ages into The Renaissance, where the technology began to catch up to the market’s needs…

To learn more about Tracx, and our next generation social sentiment analysis engine, Sentity, contact us below.

Read More

Topics: Analytics, White Paper, Sentity, sentiment,

Don't Be Fooled By "Big Data" Impostors...

Posted by Shannon Johlic on Oct 17, 2014 2:14:00 PM

Big Data is like oil resized 600

"If a data scientist could use [the product] to do something they could never do before... then call it a Big Data technology. If not, but you think the technology is great, just call it better BI." - Forbes

In a recent article published by Forbes,  the rising trend of “fake Big Data” products is discussed. As of late, more and more companies are adding the adjective “Big Data” to their marketing in hopes of gaining more traction with their target audiences.

For every business platform, there are “big data” players, and then there are Big Data players. It’s important to be able to distinguish the difference. “Big data is an all-encompassing term for any collection of data sets so large and complex that it becomes difficult to process using traditional data processing applications.” Other platforms can be grouped into a “nice to have technology” category. From research conducted by Platfora and Luth Research, 55% of respondents said that small data solutions were being repackaged as Big Data solutions. 

Riding the coat tails of a trendy and popular buzzword is nothing new in the technology market. Just as in the early days of the internet when companies were simply adding “.com” to their name to be buzz-worthy, Big Data must overcome being used simply as a buzzword within the industry. True big data companies prove they legitimately deserve this title by making access to big data more tangible and useful – making it so clear and straightforward that, according to the Forbes article, “your mom and dad could use it or a data scientist could use it to do something they could never do before”. 

To put this into perspective, the phrase “don’t talk about it, be about it” certainly applies here, as Tracx pulls data from anywhere on the Internet that a conversation can be held. Data is sliced and diced to become manageable and actionable by everyone, from community managers up to research analysts across the enterprise. The key: It’s useful. It’s efficient. It’s insightful.

“…data is like crude oil. It needs refining before it becomes gasoline.” - Joseph Tripoldi, former CMO Coca Cola.

In today’s market, data must be easily actionable to truly be considered “Big Data”, otherwise it’s simply a database of information sitting on a server. Next time you hear a company claiming they are “Big Data”, take a look at what their company actually does by asking, ”Does this product reveal insightful, new insights and allow me to use the data easily in ways I could not do before?”

Tracx does…

Read More

Topics: big data

5 Ways That Tracx Enhances Your Social Customer Care

Posted by Ben Foley on Oct 15, 2014 3:13:00 PM

tumblr n85ucuDxZj1sfie3io1 1280 resized 600

Customer loyalty has never been of more focus to big brands than it is today. Consumers these days are faced with endless choices in terms of what they want to buy, and whom they want to buy it from. The Internet allows for people to purchase practically anything, from anywhere, at any time. This has caused a culture in which brands constantly vie for consumer loyalty. But at the end of the day a consumer doesn’t always choose the best product, as there are other notable factors at play. Oftentimes, customer care plays a much larger role than most people give it credit for.

Consumers Are People

People like to be treated nicely. They like to feel as if they are individuals, that their pains matter, and that they’re not just another number representing a sale to their favorite brands. More often than not, they want to buy into the lifestyle that a brand is selling, and to feel as if they are a part of something bigger than themselves – think Nike, or Apple. Remember, they need to feel like individuals. Although the climate of competition for consumer loyalty has stiffened significantly in the past decade, the ability to connect with consumers on a beneficial and personal level has also become much easier for brands.

Social media is the key to real-time, always-on customer care

Today’s biggest brands deal with consumers scattered all over the globe, and dealing with cultural nuances, time-zone differences, and countless other obstacles can be tough from a client services perspective. Social media breaks these obstacles down, and provides a convenient, effective, and immediate forum for brands to connect with their consumers and ensure that they are having the best experience possible.

Here are 5 ways that Tracx can better your social media customer care:

1. Be Quick

In Tracx, queries are created that pull in all content that is relevant to a particular brand, their industry, or anything at all that interests them. This content, which is filterable in any way that the organization desires, is then presented in customizable, streamlined dashboards. As soon as a consumer (or potential consumer for that matter) mentions anything that is of interest, the content is presented to Tracx users immediately, and is directly actionable from within the platform. It’s never been easier to keep your finger on the pulse of what your customers are saying, and immediately engage with them accordingly in real-time.

2. Be More Personal

As mentioned above, one of the greatest, most loyalty-inspiring feelings a consumer can experience is the notion that they are much more than just a number to the organizations that they choose to give their business to. Tracx makes this concept much more tangible. Whether it’s engaging via the Tracx platform to respond to a social post publically, or sending a private direct message for complete one-on-one interaction, brands can now easily tailor responses to customer pain points with specific information provided by that customer. Consumers appreciate this personalized approach to customer care.

3. Know When To Route Issues for Greater Attention, and Act Accordingly

While using Tracx, chains of authority are created easily and effectively. If a junior brand representative isn’t ready to be directly engaging with the general public, their publishing abilities are void, yet they can still stage posts of engagement for approval that are then sent to users with higher authority. Pieces of content can also be flagged for immediate action, or tagged to a specific Tracx user. These users will then be notified both within the platform, and via email that they have social posts waiting to be actionized.

4. Create a FAQ Database

Organizations using Tracx for customer reap the benefits of proactively handling their customers with swiftness and efficiency. Additionally, by pulling in all social content relevant to your brand, it’s easy to record and categorize recurring themes when it comes to the questions that people routinely ask. This list of FAQ’s can then be turned into a FAQ database, and also used during the onboarding and training process of new client services representatives. Host the FAQ database on your organization’s website, as some customers first preference is to find the answers to their questions on their own. Tracx makes this simple and easy.

5. Monitor and Measure Your Customer Care Performance

With Tracx, organizations set definitive customer care goals, allowing for precise measurement of client services team performance. For example, an enterprise might have the goal of decreasing the average time that it takes a brand representative to respond to a customer complaint. Tracx provides firm numbers to serve as indicators to whether or not these goals are being met. Executives can look at team performance as a whole, or at an individual’s response times.

Contact us today and start delivering real-time, always on customer care with Tracx.

Read More

Subscribe by Email

about tracx

Tracx is a 360-degree social media management software (SMMS) platform delivering unified social intelligence that allows enterprises to manage, share and extract actionable insights, threats and opportunities from the social web.