Building Machine Learning Application to Spot Real vs Fake Text

July 4, 2023

A growing number of businesses are using machine learning and complex data analytics to solve various challenges. Businesses can benefit from unstructured data to the fullest extent through text classification. This article speculates the necessity of recognizing fake text from the real ones. It explains the profound character of Machine Learning and Natural Language Processing to accomplish the task. It reveals the extremity of fake text and its coexisting impact on society. This incites on building a system that detects the fake text at the right time. This article encourages one to understand how easily Machine Learning can be used to build an application to spot real and fake text. It describes ways to overcome challenges while creating the applications.


The trailing succession of digital mechanisms has been proven to be a determined crowd-puller. Growing technologies like Machine Learning and Natural Language Processing have leveraged tremendous advantages for the well-being of society. Figure 1 represents the impact of fake data on humans. Machine Learning helps society in spreading awareness and creates a positive environment for the society. It has transformed the degree of simplicity in the lives of people. But just as ease of living is a boon to humanity, likewise trusting the information around the globe raises the question on right utilization of technology. 

Digital and social media platforms also tend to become a medium of spreading fake information and mislead people [1]. Taking over other people's accounts is a popular tactic used to conceal the provenance of the organization propagating false information. At the same time, technology for fake news detection would restrict this form of defamation, thereby benefiting the society.

Figure 1: Aspects of Machine Learning impacting positively on society

Despite the fact that fake news is widely circulated on social media, research shows that human practice is more responsible for the propagation of false information than automated bots. This demonstrates that there are other options besides battling the fake news sender. Considering the politics of the nation, fake news has grown to be a key factor of both limited and maximal clashes since it is regularly used to target minorities. To fight false data, Google has unveiled a brand-new tool called "About This Result." Users can evaluate information and comprehend its source as it is accessible worldwide. It supports nine Indian languages, including Hindi, Tamil, Bengali, Marathi, Gujarati, Telugu, Malayalam, Kannada, and Punjabi. By giving consumers more context, the feature enables them to choose which websites to visit and how to get the best possible outcomes [2].

Therefore, raising public knowledge and media literacy is a crucial component of fake news detection. Spotting the difference in fake and real information at the right time is highly essential for the betterment of society.  

Building the Machine Learning Model

As Machine Learning works with numerical features, it requires the textual data to be converted to numerical data. After this, data pre-processing is carried out using Natural Language Processing. Figure 2 represents the step-by-step process to spot the difference in real and fake data.

Figure 2: Block architecture to build Machine Learning model

Data Pre-processing

Text pre-processing is the process of removing stopwords, special symbols, and numbers from the text as well as stemming and lemmatization. The text data must be fed into a vectorizer after data cleaning so that it can be transformed into numerical features.

Stop words are used to remove unnecessary words so that the system can concentrate on those that are essential. Example: {is, a, an, the, but, for, on} are the words that do not change the meaning of a sentence when they are removed.

Stemming is a method for eliminating affixes from words to reveal their basic form. It is equivalent to trimming the tree's branches back to the trunk.

Lemmatization is a word normalization technique which takes context into account and reduces a term to its logical base form, or lemma.

Vectorization is the process in which the words are converted to integers or floating-point numbers in order to be used as inputs in machine learning methods

The table 1 below differentiates among the two techniques:

Table 1: Difference in Stemming and Lemmatization

Feature Engineering

Both of these concepts can be employed for word embeddings, where the words will be transformed into vectors or numbers.

1.     Bag-of-Words (BOW) or Count Vectorizer

Primary purpose of a bag of words is to count the word's occurrence in the sentence while ignoring any semantic information. The idea is fairly simple to understand and has been put into exercise. Every word in a bag of words has a number assigned to it, which gives each word equal weight. We make advantage of the TF-IDF paradigm to overcome this. 

2.     Tf-idf (Term frequency and inverse document frequency)

This model gathers some semantic information by emphasizing unusual words over common terms. The phrase "IDF" refers to giving a greater weight to unusual phrases in the document which makes it more efficient.

Model Selection

Model selection is the process of selecting a Machine Learning model that best fits our data and ultimately results better when evaluated. The table 2 below represents a comparative analysis of various Machine Learning models. 

Table 2: Comparative analysis of Machine Learning models

Different models perform better with certain types of data as described in table 2. For instance, Naive Bayes works well when characteristics are very independent. SVM is effective when there are too many features and a moderate sized dataset. Linear regression, logistic regression, and SVM are all effective when there is a linear relationship between the dependent and independent variables. The right knowledge about these models will definitely assist an individual in selecting a model that best suits their data. If one is still unable to decide on just one Machine Learning algorithm, all the models can be compared and examined on the basis of their accuracy on the training and test sets. This will surely help in figuring out the appropriate model for their data.

An ML Model makes decisions based on what it has learned from the data, whereas a neural network arranges algorithms so that it can make decisions reliably on its own. Deep learning is a subset of machine learning, and neural networks are the foundation of deep learning algorithms.

Traditional or "non-deep" machine learning is more centered on human input. Deep learning automizes the majority of the feature extraction phase which in turn reduces the need for manual input from humans. Deep learning models like Convolutional Neural Networks (CNNs) perform efficiently on classifying images. CNNs also excel at image processing tasks such as signal processing and image segmentation. It has the ability to take in the non-labelled data in its unprocessed form and automatically identify the essential features that differentiate them to their original category.

Model Training and Evaluation

Model training is the process of dividing the dataset into training set, validation set and testing set. It is performed to train the model and make it learn about the data in order to understand and identify the good values of each feature in the data. Figure 3 below represents the splitting of the overall dataset.

Figure 3: Splitting the data for model training

The training phase uses up to 75% of the whole dataset. The training set is used to assign the weights and biases that go into the model. For the validation set, almost 15% to 20% of the data is utilized to assess initial accuracy and concurrently modify its hyperparameters. The validation data is seen by the model, but it is not utilized to learn weights and biases. And the test set uses the remaining 5% to 10% of the data for model evaluation. This data is unseen by the model and it is then tested on the basis of new data.

Model Evaluation

Any model is evaluated on the basis of matrices. They are calculated on the basis of true positives (TP), true negatives (TN), false positives (FP) and false negatives (FN). Model evaluation is the practice of leveraging multiple evaluation measures to analyze a model's performance, abilities and shortcomings. A few basic metrics used to evaluate the model are mentioned below:

1.     Accuracy

Accuracy is defined as the ratio of the number of correct predictions to the total number of predictions.

Accuracy = (TP+TN)/(TP+TN+FP+FN)

2.     Precision

Precision is the ratio of true positives to the total of true positives and false positives. It basically analyzes the positive predictions.

Precision = TP/(TP+FP)

3.     Recall

Recall is the ratio of true positives to the total of true positives and false negatives. It basically analyzes the number of correct positive samples.

Recall = TP/(TP+FN)

4.     F1-Score

The F1 score is the harmonic mean of precision and recall. It is seen that during the precision-recall trade-off if we increase the precision, recall decreases and vice versa.

F1 score = (2×Precision×Recall)/ (Precision + Recall)

Deploying and Using the Application

Model Deployment

The Machine Learning model can be moved to the deployment phase, once the model is tested and evaluated. The model can be deployed using three different environments. Google AI Platform offers a good option for building and subsequently deploying Machine Learning models. Various platforms offer deployment options for Machine Learning models, like AWS Lambda, Microsoft Azure Functions, Google Cloud Functions, Google App Engine as well as Google cloud. These platforms are for people who have built a machine learning model locally and are looking into possible deployment platforms.

Application Usage

The input to the system can be textual data or a piece of information. The ML model will process the data and classify it as a real or fake text. The most important step in preventing the spread of fake news and saving people's lives is early fake news identification [3]. Another challenge in identifying fake text is the shortage of large datasets as well as labeled datasets marked with ground-truth labels [4].


Supporting people's understanding that their news-consuming behaviors, such as liking, commenting, and sharing, might have a big impact. There is a need to create a system that keeps track of people's news-related behaviors, analyzes similarities and differences between those behaviors, and displays these actions or patterns to individuals.

Latest Blogs
This is a decorative image for: A Complete Guide To Customer Acquisition For Startups
October 18, 2022

A Complete Guide To Customer Acquisition For Startups

Any business is enlivened by its customers. Therefore, a strategy to constantly bring in new clients is an ongoing requirement. In this regard, having a proper customer acquisition strategy can be of great importance.

So, if you are just starting your business, or planning to expand it, read on to learn more about this concept.

The problem with customer acquisition

As an organization, when working in a diverse and competitive market like India, you need to have a well-defined customer acquisition strategy to attain success. However, this is where most startups struggle. Now, you may have a great product or service, but if you are not in the right place targeting the right demographic, you are not likely to get the results you want.

To resolve this, typically, companies invest, but if that is not channelized properly, it will be futile.

So, the best way out of this dilemma is to have a clear customer acquisition strategy in place.

How can you create the ideal customer acquisition strategy for your business?

  • Define what your goals are

You need to define your goals so that you can meet the revenue expectations you have for the current fiscal year. You need to find a value for the metrics –

  • MRR – Monthly recurring revenue, which tells you all the income that can be generated from all your income channels.
  • CLV – Customer lifetime value tells you how much a customer is willing to spend on your business during your mutual relationship duration.  
  • CAC – Customer acquisition costs, which tells how much your organization needs to spend to acquire customers constantly.
  • Churn rate – It tells you the rate at which customers stop doing business.

All these metrics tell you how well you will be able to grow your business and revenue.

  • Identify your ideal customers

You need to understand who your current customers are and who your target customers are. Once you are aware of your customer base, you can focus your energies in that direction and get the maximum sale of your products or services. You can also understand what your customers require through various analytics and markers and address them to leverage your products/services towards them.

  • Choose your channels for customer acquisition

How will you acquire customers who will eventually tell at what scale and at what rate you need to expand your business? You could market and sell your products on social media channels like Instagram, Facebook and YouTube, or invest in paid marketing like Google Ads. You need to develop a unique strategy for each of these channels. 

  • Communicate with your customers

If you know exactly what your customers have in mind, then you will be able to develop your customer strategy with a clear perspective in mind. You can do it through surveys or customer opinion forms, email contact forms, blog posts and social media posts. After that, you just need to measure the analytics, clearly understand the insights, and improve your strategy accordingly.

Combining these strategies with your long-term business plan will bring results. However, there will be challenges on the way, where you need to adapt as per the requirements to make the most of it. At the same time, introducing new technologies like AI and ML can also solve such issues easily. To learn more about the use of AI and ML and how they are transforming businesses, keep referring to the blog section of E2E Networks.

Reference Links

This is a decorative image for: Constructing 3D objects through Deep Learning
October 18, 2022

Image-based 3D Object Reconstruction State-of-the-Art and trends in the Deep Learning Era

3D reconstruction is one of the most complex issues of deep learning systems. There have been multiple types of research in this field, and almost everything has been tried on it — computer vision, computer graphics and machine learning, but to no avail. However, that has resulted in CNN or convolutional neural networks foraying into this field, which has yielded some success.

The Main Objective of the 3D Object Reconstruction

Developing this deep learning technology aims to infer the shape of 3D objects from 2D images. So, to conduct the experiment, you need the following:

  • Highly calibrated cameras that take a photograph of the image from various angles.
  • Large training datasets can predict the geometry of the object whose 3D image reconstruction needs to be done. These datasets can be collected from a database of images, or they can be collected and sampled from a video.

By using the apparatus and datasets, you will be able to proceed with the 3D reconstruction from 2D datasets.

State-of-the-art Technology Used by the Datasets for the Reconstruction of 3D Objects

The technology used for this purpose needs to stick to the following parameters:

  • Input

Training with the help of one or multiple RGB images, where the segmentation of the 3D ground truth needs to be done. It could be one image, multiple images or even a video stream.

The testing will also be done on the same parameters, which will also help to create a uniform, cluttered background, or both.

  • Output

The volumetric output will be done in both high and low resolution, and the surface output will be generated through parameterisation, template deformation and point cloud. Moreover, the direct and intermediate outputs will be calculated this way.

  • Network architecture used

The architecture used in training is 3D-VAE-GAN, which has an encoder and a decoder, with TL-Net and conditional GAN. At the same time, the testing architecture is 3D-VAE, which has an encoder and a decoder.

  • Training used

The degree of supervision used in 2D vs 3D supervision, weak supervision along with loss functions have to be included in this system. The training procedure is adversarial training with joint 2D and 3D embeddings. Also, the network architecture is extremely important for the speed and processing quality of the output images.

  • Practical applications and use cases

Volumetric representations and surface representations can do the reconstruction. Powerful computer systems need to be used for reconstruction.

Given below are some of the places where 3D Object Reconstruction Deep Learning Systems are used:

  • 3D reconstruction technology can be used in the Police Department for drawing the faces of criminals whose images have been procured from a crime site where their faces are not completely revealed.
  • It can be used for re-modelling ruins at ancient architectural sites. The rubble or the debris stubs of structures can be used to recreate the entire building structure and get an idea of how it looked in the past.
  • They can be used in plastic surgery where the organs, face, limbs or any other portion of the body has been damaged and needs to be rebuilt.
  • It can be used in airport security, where concealed shapes can be used for guessing whether a person is armed or is carrying explosives or not.
  • It can also help in completing DNA sequences.

So, if you are planning to implement this technology, then you can rent the required infrastructure from E2E Networks and avoid investing in it. And if you plan to learn more about such topics, then keep a tab on the blog section of the website

Reference Links

This is a decorative image for: Comprehensive Guide to Deep Q-Learning for Data Science Enthusiasts
October 18, 2022

A Comprehensive Guide To Deep Q-Learning For Data Science Enthusiasts

For all data science enthusiasts who would love to dig deep, we have composed a write-up about Q-Learning specifically for you all. Deep Q-Learning and Reinforcement learning (RL) are extremely popular these days. These two data science methodologies use Python libraries like TensorFlow 2 and openAI’s Gym environment.

So, read on to know more.

What is Deep Q-Learning?

Deep Q-Learning utilizes the principles of Q-learning, but instead of using the Q-table, it uses the neural network. The algorithm of deep Q-Learning uses the states as input and the optimal Q-value of every action possible as the output. The agent gathers and stores all the previous experiences in the memory of the trained tuple in the following order:

State> Next state> Action> Reward

The neural network training stability increases using a random batch of previous data by using the experience replay. Experience replay also means the previous experiences stocking, and the target network uses it for training and calculation of the Q-network and the predicted Q-Value. This neural network uses openAI Gym, which is provided by taxi-v3 environments.

Now, any understanding of Deep Q-Learning   is incomplete without talking about Reinforcement Learning.

What is Reinforcement Learning?

Reinforcement is a subsection of ML. This part of ML is related to the action in which an environmental agent participates in a reward-based system and uses Reinforcement Learning to maximize the rewards. Reinforcement Learning is a different technique from unsupervised learning or supervised learning because it does not require a supervised input/output pair. The number of corrections is also less, so it is a highly efficient technique.

Now, the understanding of reinforcement learning is incomplete without knowing about Markov Decision Process (MDP). MDP is involved with each state that has been presented in the results of the environment, derived from the state previously there. The information which composes both states is gathered and transferred to the decision process. The task of the chosen agent is to maximize the awards. The MDP optimizes the actions and helps construct the optimal policy.

For developing the MDP, you need to follow the Q-Learning Algorithm, which is an extremely important part of data science and machine learning.

What is Q-Learning Algorithm?

The process of Q-Learning is important for understanding the data from scratch. It involves defining the parameters, choosing the actions from the current state and also choosing the actions from the previous state and then developing a Q-table for maximizing the results or output rewards.

The 4 steps that are involved in Q-Learning:

  1. Initializing parameters – The RL (reinforcement learning) model learns the set of actions that the agent requires in the state, environment and time.
  2. Identifying current state – The model stores the prior records for optimal action definition for maximizing the results. For acting in the present state, the state needs to be identified and perform an action combination for it.
  3. Choosing the optimal action set and gaining the relevant experience – A Q-table is generated from the data with a set of specific states and actions, and the weight of this data is calculated for updating the Q-Table to the following step.
  4. Updating Q-table rewards and next state determination – After the relevant experience is gained and agents start getting environmental records. The reward amplitude helps to present the subsequent step.  

In case the Q-table size is huge, then the generation of the model is a time-consuming process. This situation requires Deep Q-learning.

Hopefully, this write-up has provided an outline of Deep Q-Learning and its related concepts. If you wish to learn more about such topics, then keep a tab on the blog section of the E2E Networks website.

Reference Links

This is a decorative image for: GAUDI: A Neural Architect for Immersive 3D Scene Generation
October 13, 2022

GAUDI: A Neural Architect for Immersive 3D Scene Generation

The evolution of artificial intelligence in the past decade has been staggering, and now the focus is shifting towards AI and ML systems to understand and generate 3D spaces. As a result, there has been extensive research on manipulating 3D generative models. In this regard, Apple’s AI and ML scientists have developed GAUDI, a method specifically for this job.

An introduction to GAUDI

The GAUDI 3D immersive technique founders named it after the famous architect Antoni Gaudi. This AI model takes the help of a camera pose decoder, which enables it to guess the possible camera angles of a scene. Hence, the decoder then makes it possible to predict the 3D canvas from almost every angle.

What does GAUDI do?

GAUDI can perform multiple functions –

  • The extensions of these generative models have a tremendous effect on ML and computer vision. Pragmatically, such models are highly useful. They are applied in model-based reinforcement learning and planning world models, SLAM is s, or 3D content creation.
  • Generative modelling for 3D objects has been used for generating scenes using graf, pigan, and gsn, which incorporate a GAN (Generative Adversarial Network). The generator codes radiance fields exclusively. Using the 3D space in the scene along with the camera pose generates the 3D image from that point. This point has a density scalar and RGB value for that specific point in 3D space. This can be done from a 2D camera view. It does this by imposing 3D datasets on those 2D shots. It isolates various objects and scenes and combines them to render a new scene altogether.
  • GAUDI also removes GANs pathologies like mode collapse and improved GAN.
  • GAUDI also uses this to train data on a canonical coordinate system. You can compare it by looking at the trajectory of the scenes.

How is GAUDI applied to the content?

The steps of application for GAUDI have been given below:

  • Each trajectory is created, which consists of a sequence of posed images (These images are from a 3D scene) encoded into a latent representation. This representation which has a radiance field or what we refer to as the 3D scene and the camera path is created in a disentangled way. The results are interpreted as free parameters. The problem is optimized by and formulation of a reconstruction objective.
  • This simple training process is then scaled to trajectories, thousands of them creating a large number of views. The model samples the radiance fields totally from the previous distribution that the model has learned.
  • The scenes are thus synthesized by interpolation within the hidden space.
  • The scaling of 3D scenes generates many scenes that contain thousands of images. During training, there is no issue related to canonical orientation or mode collapse.
  • A novel de-noising optimization technique is used to find hidden representations that collaborate in modelling the camera poses and the radiance field to create multiple datasets with state-of-the-art performance in generating 3D scenes by building a setup that uses images and text.

To conclude, GAUDI has more capabilities and can also be used for sampling various images and video datasets. Furthermore, this will make a foray into AR (augmented reality) and VR (virtual reality). With GAUDI in hand, the sky is only the limit in the field of media creation. So, if you enjoy reading about the latest development in the field of AI and ML, then keep a tab on the blog section of the E2E Networks website.

Reference Links

Build on the most powerful infrastructure cloud

A vector illustration of a tech city using latest cloud technologies & infrastructure