Adding Value to Social Media Monitoring: More Than A Word Search Game

Posted by gavinjohnston67

It is difficult to get an accurate reading on how commonly a word is used in a given society. In fact, the task of measuring word frequency fully objectively is inherently impossible. The results will always be affected by the size of the corpus and the choice of the texts entered in it. On a global scale, where words take on subtle new meanings as they are appropriated into the semiotic structure of the actor and thereby changed, the problem becomes even more obvious. Frequency means nothing without cultural context.

This is not to say that frequency isn’t important. It is important and revealing. Frequencies are only broadly indicative of cultural salience and they can only be used as one among many sources of information about a society’s cultural preoccupations. But measurements only tell part of the story. And when they are decontextualized or proscribed meanings based on the person developing the algorithm that assigns sentiment. They give a potentially false understanding. To be correctly interpreted, figures have to be considered in the context of an in-depth analysis of meanings.

If four thousand people call a product “shitty,” it is fair to say that four thousand people reacted negatively to it. But that measurement can’t tell us about the culture of those people – are they engineers addressing it from a technological angle? Are they Venezuelan students reacting to a larger political issue? We assume that a word can be easily categorized along a linear trajectory – negative/positive, etc. But this isn’t necessarily the case. Words can be studied as focal points around which cultural domains are organized. By exploring these focal points in depth, we may be able to show the general organization principles which lend structure and coherence to a cultural domain as a whole, and which often have an explanatory power extending across multiple domains.

The underlying principle lacking in current social media monitoring processes is allolexy. The term allolexy refers to the fact that the same element of meaning may be expressed in a language in two or more different ways. Just as one word can be associated with multiple meanings, one meaning can often have two or more different lexical exponents. For example, in English, I and me are allolexes of the same primitive concept (In Latin, Ego). Often allolexes of a semantic primitive are in complimentary distribution. So in English, a combination of the semantic primitives someone and all is realized as everyone or everybody. In these particular contexts –one and –body can be seen as allolexes of someone; and –thing can be seen as an allolex of something. This notion of allolexy plays a particularly important role in social media monitoring because it allows us to build inflectional categories. For example, the forms am doing, did, and will do used without temporal adjuncts convey different meanings, but when combined with the temporal adjuncts now, before now, and after now, as in the sentences below, they are in complementary distribution and can be seen as allolexes of the same primitive DO:

I am doing it now.
I did it before now.
I will do it after now.

When we apply an approach derived from an allolexical perspective, we can start to determine where sentences or words “match,” semantically, across languages, even though inflectional categories can differ considerably from language to language. In other words, if a word is taken out the process of discourse, it loses meaning and is therefore subject to interpretation that lacks a way of accounting for either semantic variance or semantic stability – it is nothing short of a guess.

In a sense it is true that words have no “fixed” meanings because meanings of words change. But if they were always fluid and without any “true” content, they could not change either. Words do have identifiable, “true” meanings, the precise outlines of which can be established on an empirical basis by studying their range of use and articulating the contexts that subtly repurpose them. The key point is that social media monitoring today does not account for semantic deviation and language as fundamentally tied to speech and discourse. For companies that take the time and effort to do that, the financial rewards are tremendous.

Social Media Monitoring, Black Friday and the Why We Buy

Posted by gavinjohnston67

There is a wild-west mentality that dominates the corporate conversation about social media. Like the cavalier approach to the internet at the close of the 20^th century, strategy appears secondary as we scramble to find meaning behind numbers and attempt to generate capital out of something that is still in its infancy. This approach is mirrored in social media monitoring, which more often than not stops with just providing data. Numbers are gathered around an area of interest, a few correlations are run between data points and the findings are handed off to the client without any emphasis what any of if really means. As we come off of Black Friday and prepare for Cyber Monday, companies are sifting through mounds of data gleaned from social media monitoring in hopes of uncovering something that will give them the absolute edge over the competition, but it means precious little if we don’t understand the deeper issues behind shopping, gift giving, consumption, etc.

Granted, data provides an answer to “what is happening,” but it fails to address “why it’s happening.” The “why” comes from anthropological analysis to data to uncover connections between data points that are normally overlooked, which provides new business opportunities and ways of messaging to customers. Anthropology works from an assumption of the inherent interconnectedness of people, focusing on culture as the starting point of investigation. People and cultures are so complex, and anthropology strives to make sense of that complexity.

Similarly, digital anthropology seeks to connect dots and uncover relationships between data points by going beyond the search for statistical significance and focusing on producing valid, actionable insights. Loosely speaking, “reliability” is the extent to which a measurement procedure yields the same answer, however and whenever it’s carried out – it’s the data in their purest form. “Validity,” is the extent to which it fives the correct answer. Imagine a spike in negative Twitter conversations in late December about your company. While the information may be statistically reliable, it lacks meaning. It doesn’t even begin to approach an understanding of “why” with any kind of depth or understanding.

All too frequently, the questions we ask and the metrics we assign to them have very little to do with the subtleties of human behavior. The data doesn’t address whom these numbers represent, what social and cultural conditions are motivating the commentary or how independent variables influence the date. The result is that we make assumptions and ask questions that are simply wrong.

To overcome these issues, an anthropologically-trained researcher (or research team) filters data through a system of questions that tie each data point back to what we know about cultural patterns and trends. For example, if there is a spike on conversations about bacon, it might be tied to agricultural conditions, but it might also be tied to the fact that Anthony Bourdain talked about bacon martinis on his show the night before. Add that the fact that people who self-identify as “foodies” have doubled in the last few years and you start to realize that the conversation isn’t so much about the product but how the product fits into the larger pattern of people living their lives. This hypothetical spike in discussion reflects the need to be part of a special group with extensive knowledge or expertise that makes them extraordinary in the eyes of other people. And that is the place real opportunity lies.

These same principles can be applied to all social media and online activity. Whether your company is selling soap or helping people make multi-million dollar transactions, human behavior is usually more complex than the numbers alone would suggest. Discovering these connections are where the real opportunities reside.

Keep in mind, other companies have the same data you do and they too are searching the web with the hope of uncovering some hidden insight. In fact, they face the same dilemma of not being able to connect the dots between seemingly unrelated topics. Uncovering these connections and understanding the reasons behind them means uncovering new revenue streams, new avenues of messaging and new business opportunities before the competition can act. Digital anthropology helps move social media monitoring from “what” to “why” to “what next.”

Reversing Roles: Online to Brick and Mortar

Posted by gavinjohnston67

There’s a simple message for most retailers that has become common in advertising discourse over the last few year: stop talking about yourselves so much.  And while I tend to agree with this point of view, what does it necessarily mean? I think it’s less about the frequency of the message and more about the nature of it. We are no longer pushing goods, we are engaging in a dialog.

Bricks and mortar retailers are at an interesting crossroads. In-store sales driven purely by price considerations are losing ground as experiential designs gain ground. And these retailers have a marvelous opportunity to learn from their fellow online team members (often forgotten in the silos that define so many businesses) and their online competitors. Just as online retailers have struggled to generate repeat sales, so too have brick and mortar spaces. But the online world has already learned an important lesson – focusing on an added value approach rather than pushing the brand will lead to greater sales and greater loyalty.

Step one is to recognize a very difficult proposition. Namely, companies are no longer in the business of pushing goods, they’re in the business of creating fans and attracting devotees. That means shifting the experience from a transaction to a dialog that puts your brand squarely in the lives of people. If you gain permission to be part of a consumer’s daily life, you become a fixture, a player on their life stage. You gain permission by sharing. You don’t gain that permission if you spend your energy yelling about yourself.  Well, obviously. But how do you do it? Increasingly, social media analysis is a large part of the equation. Indeed, this is often the starting point for a campaign because it has the greatest reach and provides a more realistic view of how the world understands and shares your brand. Online retailers were quick to embrace this idea on two levels.

First, they have generally found a way to offer an unexpected value add, such as the Zappo’s shipping and return policies. There is a clear benefit that goes beyond the economic return in that it also is a wonderful experience – tracking, cost savings and decidedly happy people. Second, is the point of social engagement and capital. Returning to the Zappo’s example, they have made the customer experience very public, displaying not only praise but the ugly side as well. Rather than resulting in people dropping the company, they have seen their social media presence (and their sales) grow, as people come to see them as genuine, down to earth and open. The people who use them become ambassadors for the brand and increase their own sense of self-worth in the process.

I am by no means suggesting that social media is the answer, but I am suggesting that social engagement by companies and brands have become an expectation for consumers, just as we expect a company to have an ecommerce presence. The difference is that while ecommerce can provide an ocean of analytics (in the purely statistical sense), they rarely get at the subtle richness of online conversations. This means going beyond collecting numbers and sentiments and digging into the underlying connections between what is written, what is shared, and how personal identity shapes how a brand is discussed, interpreted and used. Not only does such an approach allow you to map out voiced perceptions about a brand, it allows you to identify primary influencers and how it is they gain that status. Once you understand that, you can begin mapping out a plan for how you will approach your existing market as well as find new points of entry. And that’s a pretty compelling thing.

Linguistic Shortcomings of Social Media Monitoring – notes.

Posted by gavinjohnston67

I am doing it now.
I did it before now.
I will do it after now.

Personality Seepage

Posted by gavinjohnston67

My friend Bryan Crawford posted a marvelous article by Bethlehem Shoals on “Personality Seepage” yesterday that got me revisiting an issue I’d set aside, namely, the presentation of self in virtual life. Beautifully written (unlike most of my muses), the article sums up the increasing difficulty we have in separating our various senses or displays of self thanks to the digital age.

Personality seepage is the consequence of the liminality that occurs (that nether-state between one construct of reality and another), when we put too much of ourselves online at once. With the array of IM windows, boxes, and browsers all crammed together on our laptop, iPad or telephone screens, we see seepage. Personal and professional language become blurred and the lines we draw between one projection and another break down.

Of course, this leads me back to anthropologist Erving Goffman and the theoretical model in anthropology and sociolinguistics rooted in the idea of constructed identity – that we create, or adapt, based on context. As we communicate with people, we share different parts of ourselves, adopting a slightly different personas, so to speak, to fit the context. It is a co-creative act and one that has social and cultural rules that define the interaction. The written word, with no face behind it and no real direct interaction to guide our conversation through non-verbal/non-textual cues exacerbates the situation. Unlike most situations, we have no clear way to define our contexts and we juggle too many conversations at once.

More often than not, the blurring leads to expressions that can be taken as insulting or simply out of place. We inadvertently display a side of our personalities we want to stress with one person but conceal with another. So much for the praise we heap on the notion of authenticity in what we say and do. Authenticity isn’t about being “real,” it’s about a different kind of projection, one that is more about establishing a friendly context. The authenticity of a person is, in truth, the last thing we want.

But why does any of this matter? It matters because of our new love affair with social media monitoring and the ways we build products, services and messages to accommodate the virtual self. We monitor half truths and make decisions based on spurious exchanges in the virtual universe. In other words, Personality Seepage is the frequently the communicative norm in virtual space and that means the people to whom we market or for whom we build are not the people we think we know. It’s not enough to simply watch and “listen” in the social media universe. We have to understand what happens offline as well.

Linguistic Shortcomings of Social Media Monitoring – notes.

Posted by gavinjohnston67

This is not to say that frequency isn’t important. It is important and revealing. Frequencies are only broadly indicative of cultural salience and they can only be used as one among many sources of information about a society’s cultural preoccupations. But measurements only tell part of the story. And when they are decontextualized or prescribed meanings based on the person developing the algorithm that assigns sentiment. They give a potentially false understanding. To be correctly interpreted, figures have to be considered in the context of an in-depth analysis of meanings.

_g_

The Limitations of Social Media Monitoring

Posted by gavinjohnston67

Like the life of the Internet at the close of the 20^th century, there is a wild-west mentality that dominates the corporate conversation about social media. Strategy is secondary as we scramble to find meaning behind numbers and learn to generate capital out of something that is still in its infancy. But for the most part, current social media monitoring stops with providing data. Numbers are gathered around an area of interest, a few correlations are run between data points and the findings are handed off to the client without any emphasis placed on what the data means. Data provides an answer to the question “what is happening” but fails to address why it’s happening. Anthropology works from an assumption of the inherent interconnectedness of people, focusing on culture as the starting point of investigation.

It seeks to connect the dots and uncover relationships between data points by going beyond the search for statistical significance and focusing on producing valid, actionable insights. “Validity” is the extent to which it gives the correct answer. Imagine a spike in Twitter conversations in late December with negative commentary about your company. The information is statistically reliable but it lacks meaning. It doesn’t even begin to approach an understanding of “why” in any meaningful way. All too frequently, the questions asked and the metrics we assign to them have very little to do with the subtleties of human behavior. The data does not address who those people are, what social and cultural conditions are motivating the commentary, or how independent variables influence the data. The result is that we make assumptions and ask questions that are simply wrong.

To overcome these issues an anthropologically-trained researcher (or research team) filters data through a system of questions that tie each data point back to what we know about cultural patterns and trends. For example, if there is a spike in conversations about bacon, it might be tied to agricultural conditions, but it might also be tied to the fact that Anthony Bourdain talked about bacon martinis on his show the night before. Add to that the fact that people who self-identify as “foodies” have doubled in the last few years and you start to realize that the conversation isn’t so much about the product, but how the product fits into the larger pattern of how people live their lives. The spike in discussion reflects the need to be part of a special group with extensive knowledge that makes them extraordinary in the eyes of other people…or so they hope.

This same principles applies to all social media and online activity. Whether your company is selling soap or helping people make multi-million dollar transactions, human behavior is usually more complex than the numbers alone would suggest. This is where real opportunities lie.

Other companies have the same data you do. They are searching the Web with the hope of uncovering something meaningful. The good news is that they face the same dilemma of not being able to connect the dots between seemingly unrelated topics. Uncovering these connections and understanding the reasons behind them means uncovering new revenue streams, new avenues of messaging, and new business opportunities before the competition can act. Anthropology moves social media monitoring from “what” to “why” to “what next.”

By Gavin

But the Word Cloud Told Me All I Need to Know, Right?

Posted by gavinjohnston67

Social media monitoring is becoming a focal point for companies trying to figure out how social media fits into their broader strategy. Great idea, but where does it fall short? It is difficult to get an accurate reading on how commonly a word is used in a given society. In fact, the task of measuring word frequency fully objectively is inherently impossible. The results will always be affected by the size of the corpus and the choice of the texts entered in it. On a global scale, where words take on subtle new meanings as they are appropriated into the semiotic structure of the actor and thereby changed, the problem becomes even more obvious. Frequency means nothing without cultural context. So why the hell do we spend so much time doing social media monitoring without trying to really understand what the language, especially specific words, means in the broader context?

So before a marketer gets too terribly wound up about what is showing up in this week’s iteration of the social media word cloud, perhaps it makes sense to step back and think about what words mean IN CONTEXT. That means going beyond frequency and learning about the socio-cultural conditions, online and off, that shape the uses of words at different times and places. Understand the language and you understand what to do with it.

By Gavin

Follow “anthrostrategist”