Connect with us

SEO

More Automated Intent Classification Using Deep Learning

Published

on


My original plan was to cover this topic: “How to Build a Bot to Automate your Mindless Tasks using Python and BigQuery”. I made some slight course changes, but hopefully, the original intention remains the same!

The inspiration for this article comes from this tweet from JR Oakes. 🙂

As Uber released an updated version of Ludwig and Google also announced the ability to execute Tensorflow models in BigQuery, I thought the timing couldn’t be better.

In this article, we will revisit the intent classification problem I addressed before, but we will replace our original encoder for a state of the art one: BERT, which stands for Bidirectional Encoder Representations from Transformers.

This small change will help us improve the model accuracy from a 0.66 combined test accuracy to 0.89 while using the same dataset and no custom coding!

Automated Intent Classification Using Deep Learning (Part 2)

Here is our plan of action:

  • We will rebuild the intent classification model we built on part one, but we will leverage pre-training data using a BERT encoder.
  • We will test it again against the questions we pulled from Google Search Console.
  • We will upload our queries and intent predictions data to BigQuery.
  • We will connect BigQuery to Google Data Studio to group the questions by their intention and extract actionable insights we can use to prioritize content development efforts.
  • We will go over the new underlying concepts that help BERT perform significantly better than our previous model.

Setting up Google Colaboratory

As in part one, we will run Ludwig from within Google Colaboratory in order to use their free GPU runtime.

First, run this code to check the Tensorflow version installed.

import tensorflow as tf; print(tf.__version__)

Let’s make sure our notebook uses the right version expected by Ludwig and that it also supports the GPU runtime.

I get 1.14.0 which is great as Ludwig requires at least 1.14.0

Under the Runtime menu item, select Python 3 and GPU.

You can confirm you have a GPU by typing:

! nvidia-smi

At the time of this writing, you need to install some system libraries before installing the latest Ludwig (0.2). I got some errors that they later resolved.

!apt-get install libgmp-dev libmpfr-dev libmpc-dev

When the installation failed for me, I found the solution from this StackOverflow answer, which wasn’t even the accepted one!

!pip install ludwig

You should get:

Successfully installed gmpy-1.17 ludwig-0.2

Prepare the Dataset for Training

We are going to use the same question classification dataset that we used in the first article.

After you log in to Kaggle and download the dataset, you can use the code to load it to a dataframe in Colab.

Configuring the BERT Encoder

Instead of using the parallel CNN encoder that we used in the first part, we will use the BERT encoder that was recently added to Ludwig.

This encoder leverages pre-trained data that enables it to perform better than our previous encoder while requiring far less training data. I will explain how it works in simple terms at the end of this article.

Let’s first download a pretrained language model. We will download the files for the model BERT-Base, Uncased.

I tried the bigger models first, but hit some roadblocks due to their memory requirements and the limitations in Google Colab.

!wget https://storage.googleapis.com/bert_models/2018_10_18/uncased_L-12_H-768_A-12.zip

Unzip it with:

!unzip uncased_L-12_H-768_A-12.zip

The output should look like this:

Archive:  uncased_L-12_H-768_A-12.zip
   creating: uncased_L-12_H-768_A-12/
  inflating: uncased_L-12_H-768_A-12/bert_model.ckpt.meta  
  inflating: uncased_L-12_H-768_A-12/bert_model.ckpt.data-00000-of-00001  
  inflating: uncased_L-12_H-768_A-12/vocab.txt  
  inflating: uncased_L-12_H-768_A-12/bert_model.ckpt.index  
  inflating: uncased_L-12_H-768_A-12/bert_config.json

Now we can put together the model definition file.

Let’s compare it to the one we created in part one.

I made a number of changes. Let’s review them.

I essentially changed the encoder from parallel_cnn to bert and added extra parameters required by bert: config_path, checkpoint_path, word_tokenizer, word_vocab_file, padding_symbol, and unknown_symbol.

Most of the values come from the language model we downloaded.

I added a few more parameters that I figured out empirically: batch_size, learning_rate and word_sequence_length_limit.

The default values Ludwig uses for these parameters don’t work for the BERT encoder because they are way off compared to the pre-trained data. I found some working values in the BERT documentation.

The training process is the same as we’ve done previously. However, we need to install bert-tensorflow first.

!pip install bert-tensorflow
!ludwig experiment 

  --data_csv Question_Classification_Dataset.csv

  --model_definition_file model_definition.yaml

We beat our previous model performance after only two epochs.

Automated Intent Classification Using Deep Learning (Part 2)

The final improvement was 0.89 combined test accuracy after 10 epochs. Our previous model took 14 epochs to get to .66.

This is pretty remarkable considering we didn’t write any code. We only changed some settings.

It is incredible and exciting how fast deep learning research is improving and how accessible it is now.

Why BERT Performs So Well

There are two primary advantages from using BERT compared to traditional encoders:

  • The bidirectional word embeddings.
  • The language model leveraged through transfer learning.

Bidirectional Word Embeddings

When I explained word vectors and embeddings in part one, I was referring to the traditional approach (I used a GPS analogy of coordinates in an imaginary space).

Traditional word embedding approaches assign the equivalent of a GPS coordinate to each word.

Let’s review the different meanings of the word “Washington” to illustrate why this could be a problem in some scenarios.

  • George Washington (person)
  • Washington (State)
  • Washington D.C. (City)
  • George Washington Bridge (bridge)

The word “Washington” above represents completely different things and a system that assigns the same coordinates regardless of context, won’t be very precise.

If we are in Google’s NYC office and we want to visit “Washington”, we need to provide more context.

  • Are we planning to visit the George Washington memorial?
  • Do we plan to drive south to visit Washington, D.C.?
  • Are we planning a cross country trip to Washington State?

As you can see in the text, the surrounding words provide some context that can more clearly define what “Washington” might mean.

If you read from left to right, the word George, might indicate you are talking about the person, and if you read from right to left, the word D.C., might indicate you are referring to the city.

But, you need to read from left to right and from right to left to tell you actually want to visit the bridge.

BERT works by encoding different word embeddings for each word usage, and relies on the surrounding words to accomplish this. It reads the context words bidirectionally (from left to right and from right to left).

Back to our GPS analogy, imagine an NYC block with two Starbucks coffee shops in the same street. If you want to get to a specific one, it would be much easier to refer to it by the businesses that are before and/or after.

Transfer Learning

Transfer learning is probably one of the most important concepts in deep learning today. It makes many applications practical even when you have very small datasets to train on.

Traditionally, transfer learning was primarily used in computer vision tasks.

You typically have research groups from big companies (Google, Facebook, Stanford, etc.) train an image classification model on a large dataset like that from Imagenet.

This process would take days and generally be very expensive. But, once the training is done, the final part of the trained model is replaced, and retrained on new data to perform similar but new tasks.

This process is called fine tuning and works extremely well. Fine tuning can take hours or minutes depending on the size of the new data and is accessible to most companies.

Let’s get back to our GPS analogy to understand this.

Say you want to travel from New York City to Washington state and someone you know is going to Michigan.

Instead of renting a car to go all the way, you could hike that ride, get to Michigan, and then rent a car to drive from Michigan to Washington state, at a much lower cost and driving time.

BERT is one of the first models to successful apply transfer learning in NLP (Natural Language Processing). There are several pre-trained models that typically take days to train, but you can fine tune in hours or even minutes if you use Google Cloud TPUs.

Automating Intent Insights with BigQuery & Data Studio

Now that we have a trained model, we can test on new questions we can grab from Google Search Console using the report I created on part one.

We can run the same code as before to generate the predictions.

This time, I also want to export them to a CSV and import into BigQuery.

test_df.join(predictions)[["Query", "Clicks", "Impressions", "Category0_predictions", "Category2_predictions"]].to_csv("intent_predictions.csv")

First, log in to Google Cloud.

!gcloud auth login --no-launch-browser

Open the authorization window in a separate tab and copy the token back to Colab.

Create a bucket in Google Cloud Storage and copy the CSV file there. I named my bucket bert_intent_questions.

This command will upload our CSV file to our bucket.

!gsutil cp -r intent_predictions.csv gs://bert_intent_questions

You should also create a dataset in BigQuery to import the file. I named my dataset bert_intent_questions

!bq load --autodetect --source_format=CSV bert_intent_questions.intent_predictions gs://bert_intent_questions/intent_predictions.csv

After we have our predictions in BigQuery, we can connect it to Data Studio and create a super valuable report to helps us visualize which intentions have the greatest opportunity.

Automated Intent Classification Using Deep Learning (Part 2)

After I connected Data Studio to our BigQuery dataset, I created a new field: CTR by dividing impressions and clicks.

As we are grouping queries by their predicted intentions, we can find content opportunities where we have intentions with high search impressions and low number of clicks. Those are the lighter blue squares.

Automated Intent Classification Using Deep Learning (Part 2)

How the Learning Process Works

I want to cover this last foundational topic to expand the encoder/decoder idea I briefly covered in part one.

Let’s take a look at the charts below that help us visualize the training process.

Automated Intent Classification Using Deep Learning (Part 2)

But, what exactly is happening here? How it the machine learning model able to perform the tasks we are training on?

The first chart shows how the error/loss decreases which each training steps (blue line).

But, more importantly, the error also decreases when the model is tested on “unseen” data. Then, comes a point where no further improvements take place.

I like to think about this training process as removing noise/errors from the input by trial and error, until you are left with what is essential for the task at hand.

There is some random searching involved to learn what to remove and what to keep, but as the ideal output/behavior is known, the random search can be super selective and efficient.

Let’s say again that you want to drive from NYC to Washington and all the roads are covered with snow. The encoder, in this case, would play the role of a snowblower truck with the task of carving out a road for you.

It has the GPS coordinates of the destination and can use it to tell how far or close it is, but needs to figure out how to get there by intelligent trial and error. The decoder would be our car following the roads created by the snowblower for this trip.

If the snowblower moves too far south, it can tell it is going in the wrong direction because it is getting farther from the final GPS destination.

A Note on Overfitting

After the snowblower is done, it is tempting to just memorize all the turns required to get there, but that would make our trip inflexible in the case we need to take detours and have no roads carved out for that.

So, memorizing is not good and is called overfitting in deep learning terms. Ideally, the snowblower would carve out more than one way to get to our destination.

In other words, we need as generalized routes as possible.

We accomplish this by holding out data during the training process.

We use testing and validation datasets to keep our models as generic as possible.

A Note on Tensorflow for BigQuery

I tried to run our predictions directly from BigQuery, but hit a roadblock when I tried to import our trained model.

!bq query 
--use_legacy_sql=false 
"CREATE MODEL 
bert_intent_questions.BERT 
OPTIONS 
(MODEL_TYPE='TENSORFLOW', 
MODEL_PATH='gs://bert_intent_questions/*')" 

BigQuery complained about the size of the model exceeded their limit.

Waiting on bqjob_r594b9ea2b1b7fe62_0000016c34e8b072_1 ... (0s) Current status: DONE BigQuery error in query operation: Error processing job 'sturdy-now-248018:bqjob_r594b9ea2b1b7fe62_0000016c34e8b072_1': Error while reading data, error message: Total TensorFlow data size exceeds max allowed size; Total size is at least: 1319235047; Max allowed size is: 268435456

I reached out to their support and they offered some suggestions. I’m sharing them here in case someone finds the time to test them out.

Automated Intent Classification Using Deep Learning (Part 2)

Resources to Learn More

When I started taking deep learning classes, I didn’t see BERT or any of the latest state of the art neural network architectures.

However, the foundation I received, has helped me pick up new concepts and ideas fairly quickly. One of the articles that I found most useful to learn the new advances was this one: The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning).

I also found this one very useful: Paper Dissected: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding” Explained and this other one from the same publication: Paper Dissected: “XLNet: Generalized Autoregressive Pretraining for Language Understanding” Explained.

BERT has recently been beaten by a new model called XLNet. I am hoping to cover it in a future article when it becomes available in Ludwig.

The Python momentum in the SEO community continues to grow. Here are some examples:

Paul Shapiro brought Python to the MozCon stage earlier this month. He shared the scripts he discussed during his talk.

I was pleasantly surprised when I shared a code snippet in Twitter and Tyler Reardon, a fellow SEO, quickly spotted a bug I missed because he created a similar code independently.

Michael Weber shared his awesome ranking predictor that uses a multi-layer perceptron classifier and Antoine Eripret shared a super valuable robot.txt change monitor!

I should also mention that JR contributed a very useful Python piece for opensource.com that shows practical uses cases of the Google Natural Language API.

More Resources:


Image Credits

All screenshots taken by author, July 2019



Continue Reading
Click to comment

You must be logged in to post a comment Login

Leave a Reply

SEO

How to drive digital innovation necessary during the pandemic

Published

on


30-second summary:

  • COVID-19 has kept consumers in their homes, which has led to significant spikes in internet use and companies scrambling to digitize in order to meet customers where they are.
  • The ability to quickly develop digital capabilities will continue to be critical for meeting customer needs and ensuring organizations’ survival.
  • To remain competitive, companies must enhance the digital customer experiences they offer through upgraded social media, optimized conversion, strategies, better marketing research, an effective internal website search, and fresh customer touchpoints.

Emerging digital technologies like artificial intelligence (AI) and cloud computing enticed leaders with their agility and efficiency. Many companies planned to make digitization a goal for the new decade.

In hindsight, they probably wish they hadn’t waited.

The novel coronavirus upended every aspect of our lives. As businesses and governments around the world try to combat the pandemic, millions of consumers sit inside their homes. And where do people go during a government-mandated lockdown? Online.

The unprecedented shift to remote work and online learning, combined with a dramatic increase in movie streaming, videoconferencing, and social media traffic, has led to significant spikes in internet use. In this same time frame, big tech companies — the businesses at the forefront of digital innovation — have flourished, as have brands that capitalized on the power of social media engagement.

The biggest trick to digitization right now is meeting customers where they are. For example, my company, Teknicks, is working with an online K-12 speech and occupational therapy provider. When schools began transitioning to remote learning, students’ needs changed, too. We helped the provider pivot its value proposition and messaging to accommodate school districts’ new realities. By focusing on teletherapy tools and reassuring parents, we’ve seen substantial growth and brand recognition during the pandemic.

Until we find a vaccine for the novel coronavirus, your customers will likely engage with you through online channels. The ability to develop digital capabilities quickly will continue to be critical for meeting customer needs and ensuring survival for your organization. With that in mind, here’s how you can enhance your digital customers’ experiences:

1. Upgrade your social media

It’s not hard to be good at social media marketing — it’s hard to be great. As you build your audience on websites like Facebook and Instagram, be sure to engage with followers consistently. Create a content calendar mapping out your posts and sharing strategies and stick to it. These platforms are also a great channel for customer service, allowing you to provide personalized support and become instantaneously useful (something that customer support tickets and chatbots never seem to be).

If you already have a sizable engaged audience, it’s time to work on your content strategy. Don’t build your content strategy around keywords. Instead, focus on your audiences’ needs. A truly effective content strategy will be customized for the platform you’re on and will account for the user behavior most characteristic of that platform. Naturally, you will use keywords and phrases that are optimized for discoverability while maintaining authenticity.

One key strategy is to conduct marketing research using a survey. This tactic goes well beyond traditional keyword research and generates content ideas directly from your targeted audience, not a keyword tool. Surveying your prospective customers allows them to tell you what type of content they want to consume, significantly increasing the likelihood of engagement. Often, this strategy is the key to successful marketing strategy. I’ll go into more detail below.

2. Focus on and prioritize conversion optimization

Ideally, your website looks good and loads quickly, but those qualities alone don’t make a website great. The user experience that your website offers is ultimately what determines whether customers bounce in droves or actually stick around. Attempting to boost your initial traffic will exponentially increase customer acquisition costs, so improving your conversion rates via website optimization is a more affordable (and profitable) solution.

We often see double-digit increases in conversion rates on our first test. We typically focus on the most trafficked pages to increase the likelihood of big, impactful wins. There is an entire science behind conversion optimization, but the core fundamentals have remained the same for years.

To make sure your website’s architecture is seamless and intuitive, develop a conversion rate optimization strategy that works for you. This will require you to ask visitors for feedback, experiment with different messaging options, and regularly review your analytics, among other things. The idea is to get to know your visitors well. It takes work, but it will pay off over time as the incremental conversion rate increases impact top-line revenue.

3. Conduct marketing research surveys

With the right insights, you can turn every engagement into a memorable and valuable experience for both you and your customers. The best way to get customer insights is to ask. Design a survey of up to 10 questions in a variety of formats along with some screening questions to make sure the feedback you get is actually useful.

When designing, consider your potential customers’ preferences and pain points. For example, if you know your audience is mostly on Instagram, asking “What do you like about social media?” won’t be as effective as “What makes Instagram posts better than Facebook posts?” Once the survey’s drafted, post it to your social channels and send it out to your mailing list. You want to understand which messages resonate with your audience before you spend a cent on marketing. Learning how to conduct marketing research is one of the most important marketing skills you can attain.

Asking individual customers how they feel about various messaging options can give you a goldmine of useful data to help inform the language and design choices you make. Not every customer will choose to participate in a survey, but some will. Show them you appreciate their input by offering a small discount or another incentive once the survey is completed. You’ll be surprised by how many responses you get and how beneficial the precursory information is.

4. Review your internal website search

As much as you’d love for every visitor to spend hours exploring every nook and cranny of your website, most will want to get on with their lives after they’ve found what they came for. To make the process faster, you should offer some sort of internal website search functionality. If you don’t already have one, add a search box to your navigation menu.

Not every website has one, and even the ones that do have very surface-level functions. However, search bars are a valuable asset that can increase internal sessions and conversion. Internal website searchers are 216% likelier to convert, according to WebLinc. Search bars assist your visitors and expand your understanding of user behavior, providing you with the information you need in order to adjust your website accordingly.

Evaluate the effectiveness of your internal search, taking notice of how it finds and organizes the content after a search. Most native search functionality is very basic and just looks for the presence of “search term,” but you may want to test out more advanced filters that help users more effectively find the information they are looking for.

I recommend looking at the search data monthly to see what users have been looking for. Be sure to review what searches yielded zero results and which searches brought up irrelevant content. Identify areas that can be approved and understand your content gaps that need additional content to support the demand.

5. Identify new customer touchpoints

Innovation is all about using new technology to improve old processes. While your typical customer journey might depend on your industry and business, chances are good that you can find ways to enhance it with emerging technologies.

Evaluating whether an emerging technology is a fit for your business and whether you should invest in testing it out, starts with (drumroll …) a survey. As we discussed earlier, surveys can answer just about anything you want to know about your target audience. Go ahead and ask your audience if they own or use the emerging tech and validate its place in the customer journey.

Take the new home buying process, for example. David Weekley Homes, the largest privately-held home builder in the U.S., wanted to better understand whether voice-enabled devices can play a role in the customer journey. The company also wanted to propose a voice app idea to the audience and understand how they felt about the emerging technology concept. By conducting a survey, we uncovered that 81% of the respondents would consider the voice app idea to be somewhat to extremely valuable and 70% would possibly to definitely use the voice app if it existed.

The increasing usage of voice search and voice-enabled devices also offers an opportunity for consumer brands to make it easier than ever for customers to find their products. Tide, for example, has capitalized on marketing on Amazon’s Alexa Skills platform to remove a step from the purchasing process. Customers can use the company’s skill to order Tide products without having to pull up the Amazon app or go to the Tide website. In that way, new tech makes an old process (purchasing detergent) more frictionless than ever.

The COVID-19 pandemic has made digital innovation a business imperative. Regardless of your industry, you should look for ways to anticipate and meet customer needs. Your customers expect a seamless digital experience. If you can’t provide it, they won’t have to leave their homes to find someone else that can.

Nick Chasinov is the founder and CEO of Teknicks, a research-based internet marketing agency certified by Google in Analytics, Tag Manager, and a Google Premier AdWords partner.



Source link

Continue Reading

SEO

Core Web Vitals, E-A-T, or AMP?

Published

on


30-second summary:

  • The biggest Google update of the year is called the Page Experience update.
  • Core Web Vitals are part of that update, and they are definitely ranking factors to keep in mind, especially when optimizing images.
  • AMP is no longer the only way to get a “Top Stories” feature on mobile. Starting in 2021, any news webpage can become a “Top Story”.
  • Combining AMP’s privacy concerns and cost of operation might mean that AMP will disappear within a couple of years.
  • E-A-T is not a ranking factor right now, and we don’t know if it will become one in the future.

2020. What a year. History is happening around us, and Google? Well, Google keeps on revamping their search algorithms. Over the years, there have been many many major algorithm updates, as Google worked to keep us on our toes. 2020 was no different: in one fell swoop, we got the news about a Page Experience update and AMP news. All the while the debate about whether or not you need E-A-T for ranking rages on. How do the Core Web Vitals stand in changing the search game in 2021?

Let’s go over each of these innovations and see which will change the way we do SEO, and which will fade into obscurity sooner rather than later.

1. Importance of core web vitals for SEO

Core Web Vitals were part of Page Experience update, and, by far, caused the biggest ruckus.

There’s a lot to learn about Core Web Vitals, but they boil down to the three biggest issues on our webpages:

  1. LCP — Largest Contentful Paint, which deals with the loading speed of the largest single object on the page.
  2. FID — First Input Delay, which means the reaction time of the page to the first user input after (whether they click, tap, or press any keys).
  3. CLS — Cumulative Layout Shift — this is the measure of how much the content of the page jumps while loading content, mostly visual content, after opening.

How core web vitals influences rankings

Of course, some SEO experts think that the entire Page Experience update is nothing special, and could even: “[…] distract, […] from the core mission of communication and storytelling,”.

And, sure, most of Page experience update is simply an assembly of things we’ve known for a while: use HTTPS, be mobile-friendly, control your page speed, and so on.

But Core Web Vitals are a bit different and can influence the SEO practice in unexpected ways. Key factor that’s already changing rankings is Cumulative Layout Shift.

As most SEO experts know, for a while an important part of image optimization was using the <decoding=async> attribute in the <img> tag to avoid losing page speed while rendering the page.

Using <decoding=async> could lead to some seriously janky pages if coders didn’t specify the height and width of every single image to be rendered. Some websites did it anyway, for example, Wikipedia on most of its pages has a predefined space for images created ahead of time.

Core Web Vitals and other ranking factors for 2021 - Wikipedia

But as SEO experts we didn’t have to worry about pages being jumpy all too much, as that didn’t influence the rankings. Now with CLS being formally announced as a ranking factor, things will change for a whole slew of websites and SEO experts.

We’ll need to make sure that every webpage is coded with CLS in mind, with the needed space for every image defined ahead of time, to avoid the layout shifts.

The verdict

Overall, of course, it’s too early to tell, and more work by SEO’s around the web needs to be done here. However, it seems that if you aren’t used to focusing on technical SEO, Core Web Vitals becoming ranking signals might not influence your day-to-day work at all.

However, if you are conducting complicated technical SEO, then Core Web Vitals will definitely change the way you work in as-yet unexpected ways.

2. Importance of AMP for SEO

The AMP’s relevance today is kind of an open question. While it’s always been great as a quick-and-easy way to increase page speed, the privacy concerns have been voiced over and over again since the technology’s very inception.

But in 2020, significant changes are afoot, since, within the same Page Experience update, Google announced that there’s finally no requirement for us to create AMP pages to occupy the “Top Stories” SERP feature.

That’s a pretty huge step for anybody trying to accrue as many SERP features as they can, and, in particular, for news websites.

Core Web Vitals and other search ranking factors for 2021 - Top Stories

How AMP influences rankings

If we believe John Muellers’ words, then AMP is not a ranking factor. Seems plain and simple enough. But of course, things aren’t so simple, because AMP comes with pretty significant gains in page speed, and speed is an important ranking factor.

Thanks to AMP’s pre-rendering combined with some severe design limitations, AMP webpages often really do win in page speed, even if not in ranking as is.

The “Top Stories” SERP feature, however, was a huge benefit to using an AMP for any news agency with a website, and it’s easy to understand why. Just look at how much of the page is occupied by the “Top Stories” results.

Not only do “Top Stories” automatically get top 1 ranking on the SERP, but they also sport a logo of the website posting them, standing out even more from the boring old blue-link SERP.

This means that for a few years now news websites were essentially forced into using AMP to get into a “Top Stories” SERP feature on mobile since it absorbs a whole lot of clicks.

On the other hand, it takes quite a lot of resources to support AMP versions of the webpages, because you are basically maintaining a whole additional version of your website.

Added to which, a page that’s been properly optimized for speed might not need AMP for those speed gains, as well.

The verdict

While it’s tough to imagine that AMP will fade away completely within the next couple of years, AMP’s privacy issues combined with the cost of maintaining it might spell the end of it being a widely used practice.

Now, with the “Top Stories” becoming available to non-AMP pages, there’s virtually no reason to jeopardize the users’ security for speed gains you could get by proper optimization.

3. Importance of E-A-T for SEO

Expertise. Authority. Trust. All perfectly positive words and something we should all strive for in our professional lives. But what about search optimization?

Coming straight from Google’s Quality Rater Guidelines, E-A-T has been the talk of the town for a good moment now. Let’s dive in and see how they might change the way we optimize for search.

How E-A-T influences rankings

For most of us, they don’t really.

Sure, Quality Rater Guidelines provide valuable insights into Google’s ranking process. However, E-A-T is one of the lesser-important factors we should be focusing on, partly because these are nebulous, abstract concepts, and partly because Google doesn’t exactly want us to.

As Google’s official representatives informed us, E-A-T is not in itself a ranking factor.

Receiving follow-up questions, Google’s John Mueller then reiterated that point, and Ben Gomes, Google’s VP of search engineering confirmed that quality raters don’t influence any page’s rankings directly.

However, in practice, we often see that the so-called YMYL websites already can’t rank without having some expertise and authority established. A very popular example is that it’s virtually impossible to rank a website providing medical advice without an actual doctor writing the articles.

The problem here is that expertise, authority, and trustworthiness are not easily interpreted by the search algorithms, which only understand code.

And, at the moment, there seems to be no surefire way for Google to transform these signals into rankings, except to read the feedback of their quality raters before each algorithm update.

The verdict

While using E-A-T to rank websites might sound like an inarguable benefit for the searcher, there is a couple of concerns that aren’t easily solved, namely:

  1. Who exactly will be determining the E-A-T signals, and according to which standard?
  2. The introduction of such factors creates a system where the smaller and newer websites are punished in rankings for not having the trustworthiness that they couldn’t realistically acquire.

Responding to both of these concerns requires time and effort on the search engine’s side.

As things stand right now, E-A-T is not something to keep in mind while doing day-to-day SEO operations.

Let’s imagine a fantastical scenario where a webmaster/SEO expert has some free time. Then they might want to work on E-A-T, to try and stay ahead of the curve.

On the other hand, there simply isn’t any proof that Google will actually use E-A-T. Or that, even if used, these signals will become major ranking factors. For this reason, E-A-T shouldn’t be your priority ahead of traditional SEO tasks like link building and technical optimization.

Additionally, consider this. The entire Quality Rater Guidelines is 168 pages long. However, a comprehensive explanation of what E-A-T is and why it might be calculated a certain way will take many more pages than that.

Conclusion

As of the time of this writing, the Core Web Vitals seems to be the most important ranking news to come out in 2020 in practical terms. However, search is an extremely volatile field: what worked two weeks ago may not work today, and what works today might not work for most of us.

The matters are further complicated because we’re fighting an uneven battle: it’s simply not in search engines’ best interest to give us a full and detailed picture of how ranking works, lest we abuse it.

This is why it’s crucial to keep our hand on the pulse of optimization news and changes occurring every single day. With constant efforts from our SEO community to work out the best way to top rankings, it’s possible for us to close that gap and know for sure which trends are paramount, and which we can allow ourselves to overlook.

Aleh Barysevich is Founder and CMO at SEO PowerSuite and Awario.





Source link

Continue Reading

SEO

How to optimize and use effectively

Published

on


30-second summary:

  • Partial match domains refer to when your domain name has partially included the main keyword that you are trying to rank for.
  • There are many aspects that make it different from how the exact match domain works.
  • Tudor Lodge Consultants share a quick guide to help you succeed at partial match domains, understand the caveats, and optimize effectively.

Partial match domains refer to when your domain name has partially included the main keyword that you are trying to rank for.

Commonly used by SEO professionals to gain an advantage when it comes to ranking in the search engines or from business owners who have a company name that is closely linked to the services they offer or area they work in.

Examples of partial matches include having vital keywords like “insurance”, “loans”, or “casino” in the domain name or adding words like “hub”, “network”, or “quick” to the beginning or end of the domain, such as casinohub.com, everydayinsurance.com or quickmoney.com

This is different from an exact match domain (EMD) which stipulates the exact keywords you are trying to rank for in your domain name e.g carinsurance.com, plumbing.com, bestcasinos.com

Content created in partnership with Tudor Lodge Consultants.

Why can partial match domains be an issue?

Historically, having an exact match or partial match domain was a sure-fire way to rank top for your target keywords – only for Google to weigh this down considerably in recent years as a way to make SEO positions more ‘earned’ rather than ‘gained.’

Partial match and exact match domain have been shown to have a higher click-through-rate (CTR) in search results – largely because they mention the exact words that the customer is looking for. Unsurprisingly, these domains can be worth thousands and are put on sale through the likes of GoDaddy and 123 Reg.

Whilst having a partial match domain can be an advantage for SEO, there is always the risk of exposing your business to a Google penalty, especially as Google’s guidelines become more strict and give preference to brands that demonstrate good use of the content, link-building, varied traffic sources, and user experience.

Although you may demonstrate very good SEO results initially, you may find yourself compromised during the next algorithm update, which could have a massive impact on your website and its rankings – and make it very challenging to recover from the penalty. Not to mention, the financial implications to you and your client.

Therefore, being conscious of partial matches and how they work for SEO is of vital importance.

When partial match domains are high risk

Partial matches are high risk when optimizing in an industry that is very highly competitive and prone to algorithm updates – such as casino or gamblings, loans and credit, finance and insurance, web hosting, FX, and more.

Reason 1: There is a risk that you may use too many keywords in your URL, meta-data, and content and this is deemed as keyword stuffing by Google and is therefore penalized in the next update.

Reason 2: You may be generating links back to the site, but getting your brand name linked back to the site might be considered overkill if it mentions high-risk words like “casino”, “loans”, or “insurance” too often.

When partial match domains are low risk

Partial match domains are low risk when targeting local SEO searches (that is, a location) or the keywords are not competitive.

After all, if you have the domain name malibu-hairdressers.com, there are only going to be a handful of hairdressers in the Malibu area to compete against and this is a viable name for a company in that area. Also, local SEO searches are not often included in algorithm updates, which makes them a safer bet and you can always gain good and free exposure through the three results that feature on Google Local Listings.

If your keywords are not competitive and you are more or less the only person in your industry, you should be low risk, since you may not need many optimizations to get to position one of Google and the role of keyword stuffing does not come into play as much.

In addition, if your website is an information resource, you are trying to capture lots of search phrases and not heavily relying on just a few that might be struck by an algorithm. A website that is full of guides or news, should generate content and links more naturally, even though it has a partial match domain. Successful examples of sites like this include searchenginewatch.com, moneyadviceservice.co.uk, and smcrcompliance.com.

How to optimize partial match domains

1. Be as natural as possible

If you have a partial match domain and are already optimizing it, try to make the SEO as natural as possible. Create good quality content guides or blog posts and when getting links, drive them towards these pages, not your money pages.

If you are linking back money pages, use anchor like ‘read more’ or ‘find out more’ to hyperlink back to them. Try to stay clear or exact match or partial match anchor text as this could be seen as too spammy. It’s not too late to message all the links you have generated so far and get them redirected to safer pages or blog posts on your website. This approach may take longer but will be much more safer and effective long-term.

2. Manage your keyword stuffing

Try and avoid using the main keyword like “casino” or “insurance” too often. One of the simplest ways is to mention it one only in the meta-title, meta-description, and URL too.

Rather than: quickcarinsurance.com/car-insurance

Use: quickcarinsurance.com/car

3. Try to avoid using one from the start

If you can avoid using a partial match domain from the start, this would be ideal. As SEOs, we never know what is round the corner with Google’s guidelines, but we can certainly see the trend of brands taking center stage on page one. So with this in mind, try using a brand name if you can.

Be clever with your domain name: You do not necessarily have to include the money word to get the value of a high-click-rate. You can be smart with your domain choices, such as the company Fetch.com which is a pick-up delivery app, or Paw.com for dog accessories, or GetIndemnity.co.uk, the large business insurance broker. Think of good synonyms or words connected to the brand, without compromising your Google ranking.

4. Manage the expectations of your client

The majority of SEO clients want quick results, even though we really need six to 12 months (or longer) to show the full impact of our work. When pitching to a client with a partial match or exact match domain, you need to manage expectations that there might be a fall in rankings during the course of a year due to an algorithm change – and you may need to make changes for this to recover. Someone with a long-term view on their SEO will appreciate this, but someone who wants quick results will not and will likely demand their money back before you know it.



Source link

Continue Reading

Trending

Copyright © 2019 Plolu.