Download as pdf or txt
Download as pdf or txt
You are on page 1of 19

HINDUSTHAN Educate Empower Excel

College of Engineering and Technology

Project PHASE II
HINDUSTHAN Educate Empower Excel

College of Engineering and Technology


DEPRESSION DETECTION USING SVM

TEAM MEMBERS:
AMEER ALI S (20104008)
ASWAJITH K S (20104013)
RITHESH R (20104049)
VIGNESH T K (20104062)
PROJECT SUPERVISOR:
Ms.GAYATHRI M.E
ASSOCIATE PROFESSOR
Educate Empower Excel
PROJECT PHASE 2 Department of CSE 2
ABSTRACT
● Depression is a big concern nowadays. Our project uses technology to
spot signs of depression in text messages.

● We clean up the text by doing things like removing unnecessary words


and breaking words down to their simplest form.

● Our approach involves analyzing the language used in messages to detect


common patterns and expressions associated with depression.

● We picked a specific method called SVM to help us figure out if a text


message shows signs of depression.

Educate Empower Excel 3


PROJECT BASED LEARNING REVIEW I
SYSTEM ARCHITECTURE

Educate Empower Excel 4


PROJECT BASED LEARNING REVIEW I
LITERATURE SURVEY
Sl.No. Title Author Objective Methods/Algorithms/Hardw
are

1 literature review on depression detection. Guntuku Sai Analyze existing research on depression Machine
Sruthi, Natalia detection using social media data.Focuses Learning,Classification
Sobreira Lopes, on studies that employ linguistic feature
and Marcos extraction (e.g., word usage patterns),
André Gonçalves machine learning algorithms (for
(2021) classification), and various statistical
analysis methods.

Machine Learning Algorithms for Depression:


Diagnosis, Insights, and Research Directions
2 Pranjal Gupta, Review the application of machine learning ,Support Vector Machine
Suman Kumar, algorithms for depression diagnosis and (SVM) with radial basis
and Ashish explore future research directions.Discusses function (RBF) ,Ensemble
Khanna (2023) various machine learning algorithms Models
(Support Vector Machines, Random
Forests, etc.) used for classification based
on diverse data sources like text, speech,
and physiological signals.
LITERATURE SURVEY
Sl.No. Title Author Objective Methods/Algorithms/Hardw
are

3 A systematic review on automated clinical Ruiwei Huang, Evaluate the effectiveness of automated Natural Language
depression diagnosis: Current status and future Yufeng Wu, methods for diagnosing depression.Covers PRocessing,MAchine
directions Xiaohua Zhou, a wider range of technologies including text Learning
and Yiru Guo mining, sentiment analysis (for analyzing
(2023) social media text), and machine learning
models for classification based on various
data sources (text, speech, facial
expressions).

4 Depression Detection from Speech Using Noorfaridah M. Focuses on speech analysis techniques like MFCC,Support Vector
Machine Learning: A Review Nasir, Nornadiah feature extraction (pitch, MFCCs) and Machine (SVM) ,Hidden
Yahya, and machine learning algorithms (Support Markov Models
Rosseni D. Ishak Vector Machines, Hidden Markov Models)
(2022) for depression classification based on
speech patterns.
LITERATURE SURVEY
Sl.No. Title Author Objective Methods/Algorithms/Hardw
are

5 Deep Learning for Depression Detection: A Xin Xu, Yanan Analyze the use of deep learning techniques Convolutional Neural
Review Wang, Xiaoxiao in depression detection.Explores deep Network,Recurent Neural
Sun, and Bin Guo learning architectures like Recurrent Neural Network
(2020) Networks (RNNs) and Convolutional
Neural Networks (CNNs) for depression
classification based on text data, speech
recordings, and facial expressions.

The Role of Smartphone Sensing in Depression Maria Mavrikou, Review the potential of smartphone sensors accelerometer, gyroscope,
6 Detection: A Systematic Review Konstantinos for depression detection.Investigates the use GPS
Mousas, Yannis of smartphone sensors (accelerometer,
Kompatsiaris, gyroscope, GPS) to track physical activity
and Stefanos patterns and location data, potentially
Georgoulas linked to depression symptoms.
(2019)
LITERATURE SURVEY
Sl.No. Title Author Objective Methods/Algorithms/Hardw
are

7 Multimodal Depression Detection: A Review Yang Gao, Jingyu Analyze research on multimodal depression Natural Language Processing,
Zhang, detection methods that combine various
Chongyang data sources.Discusses the use of multiple
Zhang, and Lei data modalities like text, speech, facial
Wang (2022) expressions, and physiological signals for
more comprehensive depression detection
through machine learning approaches.

8 Artificial Intelligence for Depression Detection Michael T. Explores various AI techniques including Machine learning, natural
and Mental Health Interventions: A Review Treadwell, machine learning, natural language language processing (NLP)
Michael R. processing (NLP) for text analysis, and
Lichtenfeld, and chatbots for potential therapeutic
Jessica A. Reiss applications.
(2020)
EXISTING SYSTEM
● BERT-based Models: BERT and similar transformer-based models are
utilized for depression detection by understanding the context and
semantics of text data, enabling the identification of subtle linguistic cues
associated with depression.
● Sentiment Analysis Approaches: Some systems employ sentiment
analysis techniques to gauge the emotional tone of text data. By analyzing
sentiment, these systems can identify negative emotions commonly linked
to depression.
● Social Media Monitoring Tools: Platforms and research projects monitor
social media for depression signs. These tools leverage machine learning
algorithms to analyze users' posts, comments, and interactions, detecting
indicators of depression and other mental health issues.
Educate Empower Excel 9
PROJECT BASED LEARNING REVIEW I
PROPOSED SYSTEM
● SVM Implementation: The system uses Support Vector Machine (SVM)
to identify signs of depression in text data.

● Preprocessing: Before inputting data into the SVM model, the system
preprocesses text messages. Tasks include tokenization, stop word
removal, and lemmatization to ensure data readiness.

● Feature Extraction: Relevant features are extracted from preprocessed


text messages to represent them numerically.

● Training with Labeled Data: The system trains the SVM classifier using
a labeled dataset of text messages annotated for depression indicators.
Educate Empower Excel 10
PROJECT BASED LEARNING REVIEW I
MODULE DESCRIPTION
Natural Language Processing

• Natural Language Processing (NLP) involves the interaction between


computers and human languages.
• NLP enables computers to understand, interpret, and generate human
language in a meaningful way.
• NLP encompasses various tasks such as text classification, sentiment
analysis, and machine translation, employing techniques like tokenization,
part-of-speech tagging, and named entity recognition.
• NLP finds applications in machine translation, chatbots, sentiment analysis,
information retrieval, and text summarization, among others.

Educate Empower Excel 11


PROJECT BASED LEARNING REVIEW I
Lemmatization

• It involves reducing words to their base or dictionary form, known as the


lemma.
• Lemmatization considers the context and morphological analysis of
words to identify their root forms.
• Lemmatization helps in language understanding tasks by reducing word
variations to their common base form.
• For instance, the word "running" would be lemmatized to "run", and
"better" to "good".

Educate Empower Excel PROJECT BASED LEARNING REVIEW I 12


Vectorization

• Vectorization is a process of converting non-numeric data, such as text or


images, into numerical vectors that can be understood by machine
learning algorithms.
• It transforms raw data into a structured format of numerical values
arranged in vectors.
• Bag-of-words represents text as a matrix where rows correspond to
documents and columns correspond to unique words, with values
indicating word frequencies.

Educate Empower Excel PROJECT BASED LEARNING REVIEW I 13


SCREEN SHOTS

Educate Empower Excel 14


PROJECT BASED LEARNING REVIEW I
SCREEN SHOTS

Educate Empower Excel 15


PROJECT BASED LEARNING REVIEW I
SCREEN SHOTS

Educate Empower Excel 16


PROJECT BASED LEARNING REVIEW I
SCREEN SHOTS

Educate Empower Excel 17


PROJECT BASED LEARNING REVIEW I
Thank you
Educate Empower Excel 18
PROJECT BASED LEARNING REVIEW I

You might also like