Natural Language Processing: Sentimental Analysis of Facebook Feeds

Check out more papers on Facebook Social Networking

Worldview Approach

Legal science is the uses of logical standards to issues of legitimate issues and criminal examination. The Law (the standard) is a legitimate guideline ordered by dictators to drive individuals to pursue genuinely, and any individual who neglects to agree to the law will be given unfriendly activities. The Laws might be sanctioned to characterize the principles of the

Don't use plagiarized sources. Get your custom essay on

“Natural Language Processing: Sentimental Analysis of Facebook Feeds”

Get custom essay

Connections between individuals or individuals and the State or in administering the nation. As more Research are already done with the Sentimental Analysis which can be taken as the worldwide approach toward this problem out of which that are accounted in this research are as follow. The constructed an intelligent model for sentiment analysis from MySpace member’s comments with the help of data mining. The data mining approach consists of opinion mining or sentiment analysis phases. The methodology is to have opinion mining approach to gender differences in the expression of emotion applied for MySpace sites member’s comments. The sample dataset was collected from MySpace social network sites member’s profiles containing 819 public comments or from 387 comments of normal U.S MySpace members. The experiment result showed that two thirds of the comments included positive emotion excluding 9% of 20 parts. Females have more positive attitude than males for positive comments but there is no distinction for negative comments by female or male (M. Thelwall, 2010).

A learning based classifier is built using various classification algorithms such as Bi-nary Logistic Regression, Naive Bayes, Support Vector Machine (SVM), Bayes Net and J48 and these experiments on the 2016 live news feeds showed that the proposed approach could achieve significantly improved performance for structuring the data On Facebook using SVM classifier learning model. (Shankar Setty, 2014). As the above analysis is concerned, this are worldwide perspective of the sentimental analysis of the Facebook feeds, which we are trying to achieve in the research to accomplish the paper.

Research Design

The main methodology for Sentiment Analysis is the Classifier method specifically the Naive Bayes Classifier Method where in a status update is being classified as positive or negative.

As the classifier is the main part of the analysis which would generate the final results while we provide the classifier with the training set of the positive and negative feed with the Facebook feeds update with which the algorithm will process all the status and we can get the results as expected. Below is the explanation of Naive Bayes classifier how is it going to work.

Naive Bayes Classifier

This Classifier is based on the Bayes rule , which is a way of looking at the conditional probabilities in more convenient way . Such for example A conditional probability of event C will occur given with the evidence of event X. That is normally written as P(C | X). The Bayes Rules allows us to determine this probability when all we have the probability of the opposite result and the two components individually. Working with this classifier would be much more easy as we already have sample of the training set which has the positive and the negative feeds of the Facebook data.

The perspective that renders this procedure an “naive” Bayesian one is that we make a substantial supposition about how we can compute the likelihood of the record happening; it is equivalent to the result of the probabilities of each word inside its event. This suggests there is no connection between single word and another word. Freedom suspicion it is called. As when in the process while using the naïve bayes classifier , most important thing to be included is the corpus creation as the most of the

Method of Data Collection

In this stage, clients can send a companion solicitation to every one of the general population and just the individuals who acknowledge his/her companion demand, the client can begin visiting with him/her. In a similar way other individuals can likewise send a companion solicitation and it is dependent upon the client to acknowledge the companion demand or erase the companion demand. On the off chance that the companion demand sent by the client is erased then the client cannot talk with that individual. When the companion demand is acknowledged among clients

At that point, the clients can share pictures, post messages and can begin visiting with their companions. As having the Facebook account we can get the feeds from all the fried list of the individual account holder whose account we are logged in so with this the Facebook feeds can collected as the data and can be best used for the analysis which we are been working on.

Method of Data Analysis

In this methodology, we are arranging the info content into various feelings by finding the passionate substance from the given English content. The enthusiastic substance are action words, intensifiers, descriptors, expressions or blend of these watchwords. For instance, “We are going on an excursion. I’m extremely energized”. The catchphrase “energized” speaks to “joy” or “delight”, utilizing such watchwords feelings can be characterized. The wellspring of information to the framework is literary substance from Social Networking Sites Example Facebook .

As we are taking the Facebook feed as the data to analyze before we process the data in the Naive Bayes Classifier pre-processing of the data is needed. There are various method of processing such data, which would deal with the punctuation and stop words, repeated words, Capitalization etc.

Figure 2 describes the flow of the process of naïve bayes classifier it starts with the data extraction from the Facebook feeds which are been feed to Corpus Building which are been fed to the classifier with the sample data which gives us the sentimental analysis which is been expected with the positive and negative feed.

References

  1. Ahmed Aly Hegazy, C. D. (Dec 2018). Open-sourcing PyText for faster NLP development. facebook Artificial Intelligence .
  2. Anchatgeri, M. S. (May 2018). The Facebook Analysis using Natural Language Processing (NLP). International Research Journal of Engineering and Technology.
  3. Bogdan Batrinca, P. C. (Feb 2015). Social media analytics: a survey of techniques, tools and platforms. AI & SOCIETY, 89-116.
  4. Farzindar, A. (Aug 2015). Natural Language Processing for Social Media. Synthesis Lectures on Human Language Technologies.
  5. M. Thelwall, D. W. (2010). Data Mining Emotion in Social Networking Communication: Gender Differences in MySpace. Journal of the American Society for.
  6. Shankar Setty, R. J. (2014). Classification of Facebook News Feeds and Sentiment Analysis. IEEE.
Did you like this example?

Cite this page

Natural Language Processing: Sentimental Analysis of Facebook Feeds. (2021, Apr 10). Retrieved October 4, 2022 , from
https://studydriver.com/sentimental-analysis-of-facebook-feeds/

Save time with Studydriver!

Get in touch with our top writers for a non-plagiarized essays written to satisfy your needs

Get custom essay

Stuck on ideas? Struggling with a concept?

A professional writer will make a clear, mistake-free paper for you!

Get help with your assigment
Leave your email and we will send a sample to you.
Stop wasting your time searching for samples!
You can find a skilled professional who can write any paper for you.
Get unique paper

Hi!
I'm Chatbot Amy :)

I can help you save hours on your homework. Let's start by finding a writer.

Find Writer