A Knowledge Based Recommendation System That Includes Sentiment Analysis and Deep Learning

For More Details Contact
Name:Venkatarao Ganipisetty
Mobile:+91 9966499110
Email :[email protected]
Website:www.venkatjavaprojects.com
Abstract:
Online social networks provide relevant information on users' opinion about different themes. Thus, applications, such as monitoring and recommendation systems (RS) can collect and analyze this data. This paper presents a knowledge-based recommendation system (KBRS), which includes an emotional health monitoring system to detect users with potential psychological disturbances, specifically, depression and stress. Depending on the monitoring results, the KBRS, based on ontologies and sentiment analysis, is activated to send happy, calm, relaxing, or motivational messages to users with psychological disturbances. Also, the solution includes a mechanism to send warning messages to authorized persons, in case a depression disturbance is detected by the monitoring system. The detection of sentences with depressive and stressful content is performed through a convolutional neural network and a bidirectional long short-term memory - recurrent neural networks (RNN); the proposed method reached an accuracy of 0.89 and 0.90 to detect depressed and stressed users, respectively. Experimental results show that the proposed KBRS reached a rating of 94% of very satisfied users, as opposed to 69% reached by a RS without the use of neither a sentiment metric nor ontologies. Additionally, subjective test results demonstrated that the proposed solution consumes low memory, processing, and energy from current mobile electronic devices.

Now-a-days all peoples are using online social networks (OSN) to express their views on any matter like politics, sports, educations, personal problems etc. User post their views on OSN networks and in this paper author is analysing those post or messages with deep learning BLSTM (Bidirectional Long Short Term Memory (Neural Network) to detect user’s mental conditions. In this paper first BLSTM will be trained with accessor (or OSN messages dataset) messages and then application will read OSN messages to detect user mental condition. BLSTM will predict state by analysing OSN messages from -5 to + 5 range. If user messages contains stressed words such as SAD, Lonely, failure lost etc then BLSTM will assign that message with negative sentiment and then ask application to recommend positive or motivational messages to such user.
All existing application using traditional algorithms such as Random Forest or SVM to detect sentiments from user messages but those algorithms accuracy is not better and they are not maintaining user personal information such as their personal profile to send motivational messages in ontologies. Propose work maintain all user details such as personal or professional profile, sleeping hours and age etc.
In this paper author propose concept called eSM2 (sentiment metric) with Knowledge Based Recommendation System (KBRS). Using eSM2 we will detect sentiment intensity from messages and then using KBRS we will recommend motivational messages to users. Working procedure of this technique describe below
The KBRS contains the emotional health monitoring system, which uses the deep learning model and the sentiment metric named eSM2. The sentences are extracted from an OSN and then emotional health monitoring system identifies which sentences present a stress or depression content using machine learning algorithms and the emotion of the sentence content. The monitoring system is able to send warning message to people that are previously registered. Later, the selected sentences are analysed by the sentiment metric (eSM2) and the sentiment intensity is used as input of the recommendation engine. The KBRS server establishes a communication with the KBRS client application, in which the user receives a specific message according to his/her profile, ontology aspects, and the sentiment value calculated from his/her sentences extracted from OSNs.
To implement this project author has built his dataset by hiring accessor and make them to write sentences on OSN networks and then by using those sentences he train BLSTM and random forest algorithm but here we don’t have any person to write OSN sentences so I am directly using OSN dataset from twitter and then training BLSTM and Random forest train model to calculate their accuracy and to predict sentiment from new test messages.

Check this video out President Obama at the White House Correspondents Dinner ?
Karoli I firmly believe that ObamaPelosi have ZERO desire to be civil Its a charade and a slogan but they want to destroy conservatism ?
?
?
?
i am stressed
completely lost
All bold sentences are test messages and this messages contain emoticons also.