Question 1

What is Machine Learning?

Accepted Answer

ML or Machine Learning is an AI application (Artificial Intelligence) and refers to algorithms that automatically improve themselves through experience. Those ML algorithms are used where it is hard/impossible to use conventional ones and therefore are applied in various fields. In a business context, ML is often referred to as predictive analytics.

Machine Learning can be either supervised or unsupervised.

Question 2

What is supervised learning?

Accepted Answer

In supervised learning, you have an input variable, a (correct) output variable, and an algorithm trying to map the function from input to output. It's called "supervised" as the process of learning with a correct example is similar to a teacher supervising the learning process.

The goal is to train the function so that it automatically arrives at the correct output for any given input.

In contrast, there is unsupervised learning, where only input variables exist. As there is no correct answer, algorithms are left on their own to discover and present exciting structures in the data (patterns).

Question 3

What is Deep Learning?

Accepted Answer

Deep Learning is a Machine Learning method based on Artificial Neural Networks (ANN). It is called "deep", because of multiple layers in the network and imitates the data-processing and pattern-creating work of the human mind. Deep Learning AI can learn without human supervision, and we use it for a variety of fields.

Question 4

What is Text Analysis?

Accepted Answer

Text analysis or text mining describes the process of computational text analysis. In contrast, Text Analytics, which differs subtly, is about bringing textual content to a level to be represented as data to be mined for insights/patterns. In its simplest form, Text Analysis is about counting words and the relationship between them.

Question 5

What is NLP / NLU?

Accepted Answer

As high as the value of making computers understand real-world language is, it is as complex as it is for them to comprehend it and take action truly. Therefore the field of NLU/NLP is quite old and dates back to the 1950ies.

Both concepts deal with the relationship of natural language (of humans) to AI (Artificial Intelligence) and share the common goal of making sense of language. NLP focuses on how computers can constructively process natural language. WE apply it in speech recognition, natural language understanding as well as natural language generation. NLU is a subtopic of NLP, focusing on machine reading comprehension. In other words: understanding what text means.

Only a few computer programs can make real sense of textual data. Our AI, one of them, can understand textual context, making it possible for DeepOpinion to offer best-in-class Opinion Mining.

Question 6

What is a Neural Network?

Accepted Answer

Neural Networks are composed of various layers and form the base of Deep Learning. They take in data, train themselves to recognize patterns, and generate an outcome. Amongst the training process, the connections between the different layers adapt ("learn") to better predict the result for a similar set of data.

The applications of NNs are far-fetched and can already be seen in everyday life (i.e., facial recognition or financial forecasting).

Question 7

Can I become part of the team?

Accepted Answer

See our career page to learn more about open positions, how we work and why we do what we're doing. Of course, there’s always the chance to let us know that you are interested in working at DeepOpinion.

Question 8

What is The Data Structure of Batch Analysis Results for Opinion Mining

Accepted Answer

What is Aspect-based Sentiment Analysis

Aspect-based sentiment analysis refers to the task of identifying fine-grained opinion towards a specific topic in text. This text can take a variety of formats such as emails, product reviews, customer requests, social media posts, and any other user generated content. This approach to text analysis is considered the industry standard for analyzing customer reviews as seen in the image below.

https://malcolm-en-gb.s3.eu-west-1.amazonaws.com/instances/oiJS2eQZyE/resources/tIC9tp5U72/Amazon_review_absa.png (Amazon_review_absa.png)

How A Customer Review is Structured

A customer review consists of two main parts; the review text and review description or metadata such as name, date, rating, etc. This universally applies to most online reviews including Amazon product reviews, Google Maps company reviews, tweets, and more.

https://malcolm-en-gb.s3.eu-west-1.amazonaws.com/instances/oiJS2eQZyE/resources/l4s3zEcKGK/Amazon_review_detailed.png (Amazon_review_detailed.png)

Reviews tend to be dense with mentions of topics, emotions, and sentiments as customers are expressing their experience in a short message. You would hence find reviews that include multiple sentences. Therefore, we unpack a review to its core elements which we refer to as segments (eg, sentences). This way we ensure high accuracy and provide you with all the essential analysis you require to know about a review.

https://malcolm-en-gb.s3.eu-west-1.amazonaws.com/instances/oiJS2eQZyE/resources/mZxanVYcir/Review_text_segments.png (Review_text_segments.png)

To get fine-grained analysis the review is broken-down to 3 levels. Level 1 is the whole review message, Level 2 is a breakdown of the segments in the review text, and Level 3 are the topics and sentiments associated with each segment which can be none, one, or more. The diagram below illustrates this hierarchy.

https://malcolm-en-gb.s3.eu-west-1.amazonaws.com/instances/oiJS2eQZyE/resources/z4o5iQ1knZ/Absa_structure.png (Absa_structure.png)

Your analysis results will also include a unique ID for each level to give it a convenient structure and make working with it easy in your desired application.

https://malcolm-en-gb.s3.eu-west-1.amazonaws.com/instances/oiJS2eQZyE/resources/O1A0Q5wNuX/Review_absa_structure.png (Review_absa_structure.png)

How Our Analysis Results are Structured

It is common to upload a file with 100 rows (1 review per row) and download results with 300 rows for example. This is because each of these reviews would have multiple sentences that can mention 1 or more topics. To make results easy to work with, we add a new row for each topic identified in each segment.

For example, if you have a review consisting of 2 sentences and each sentence has 2 topics mentioned, you will end with 4 rows for this review. The review text will appear 4 times, each segment will appear twice, and each topic is considered unique to a segment. This way you get a layered/nested results ready for your following activities.

Example of input file with 50 rows (50 reviews)

https://malcolm-en-gb.s3.eu-west-1.amazonaws.com/instances/oiJS2eQZyE/resources/8FBcj8CvX2/Screen%20Shot%202021-10-30%20at%203.07.06%20PM.png (Screen Shot 2021-10-30 at 3.07.06 PM.png)

Example of output file with 280 rows (50 reviews)

Having more rows in the results is an indicator of the richness of the data. You will also notice some column headers are highlighted in blue color. These columns are generated by DeepOpinion Studio.

https://malcolm-en-gb.s3.eu-west-1.amazonaws.com/instances/oiJS2eQZyE/resources/3d2iVLcpzl/Screen%20Shot%202021-10-30%20at%2012.27.08%20PM.png (Screen Shot 2021-10-30 at 12.27.08 PM.png)

Results Data Dictionary

Here is a description of the columns you can expect from your analysis.

id [Level 1]: A system generated unique ID for each original row (document or review)

Text [Level 1]: The original text uploaded for automated analysis (document or review)

Segment id [Level 2]: A system generated unique ID for each segment in the original row (child of id)

Segment text [Level 2]: A segment of the original text uploaded for automated analysis (child of text)

Span start [Level 2]: The character count of where a segment starts (child of text)

Span end [Level 2]: The character count of where a segment ends (child of text)

Tag id [Level 3]: A system generated unique ID for each topic identified in a text segment (child of segment id)

Aspect [Level 3]: A topic identified in a text segment (child of segment text)

Sentiment [Level 3]: A sentiment category identified in a text segment (child of segment text)

Others [Level 1]: Any other column included in the original data such as dates, names, ratings, and source (metadata)

Why This Structure

This data structure has been carefully designed to make the results convenient to work with in downstream tasks such as in process automation or data visualization. For example, you might be interested in counting how often do your customers complain about battery life and auto-create a support ticket for each time this is mentioned.

https://malcolm-en-gb.s3.eu-west-1.amazonaws.com/instances/oiJS2eQZyE/resources/IGmg4MO3NV/Ticket_automation_freshdesk_animated.gif (Ticket_automation_freshdesk_animated.gif)

Contact us to know more about moving your customer review from static insights to dynamic and automated actions

Question 9

How do I create a custom model on DeepOpinion Studio?

Accepted Answer

Create your own custom text analysis model easily on DeepOpinion Studio in a few hours. or even minutes if you already have training data! This tutorial will follow the steps shown in the diagram below.

https://malcolm-en-gb.s3.eu-west-1.amazonaws.com/instances/oiJS2eQZyE/resources/dRKsa3NnnM/Workflow_Graphic_AutoNLU-2525951.png (Workflow_Graphic_AutoNLU-2525951.png)

This short tutorial explains how to a custom model for analyzing hotels reviews. The same steps can be followed to customize any model. You can download this Hotel Reviews Training Data to do it yourself.

Follow this step-by-step guide to learn how:

Leave us a comment you would like more details.

Question 10

How do I create a document information extraction model on DeepOpinion Studio

Accepted Answer

Create a document information extraction as a cognitive skill on DeepOpinion Studio then upload and label your documents to be able to train a model.