Text detection using Python (original) (raw)

Last Updated : 12 Jul, 2025

Python language is widely used for modern machine learning and data analysis. One can detect an image, speech, can even detect an object through Python. For now, we will detect whether the text from the user gives a positive feeling or negative feeling by classifying the text as positive, negative, or neutral. In the code, Vader sentiment analysis and Tkinter are used. Tkinter is a standard GUI library for creating the GUI application.

Required Installations in Anaconda:

conda install -c anaconda tk

Linux users can also use the below command.

sudo apt-get install python3-tk

conda install -c anaconda nltk

Using pip.

pip install nltk

conda install -c conda-forge numpy

Using pip.

pip install numpy

conda install -c anaconda pandas

Using pip.

pip install pandas

conda install -c conda-forge matplotlib

Using pip.

pip install matplotlib

VADER Sentiment Analysis

VADER (Valence Aware Dictionary and sEntiment Reasoner) is a lexicon and rule-based sentiment analysis tool that is specifically attuned to sentiments expressed in social media. VADER uses a combination of A sentiment lexicon is a list of lexical features (e.g., words) which are generally labeled according to their semantic orientation as either positive or negative. VADER not only tells about the Positivity and Negativity score but also tells us about how positive or negative a sentiment is.

Note: For more information, refer to Python | Sentiment Analysis using VADER.

Below is the implementation.

Python3 `

import time import pandas as pd import numpy as np import matplotlib.pyplot as plt from tkinter import * import tkinter.messagebox from nltk.sentiment.vader import SentimentIntensityAnalyzer

class analysis_text():

# Main function in program
def center(self, toplevel):
    
    toplevel.update_idletasks()
    w = toplevel.winfo_screenwidth()
    h = toplevel.winfo_screenheight()
    size = tuple(int(_) for _ in 
                 toplevel.geometry().split('+')[0].split('x'))
    
    x = w/2 - size[0]/2
    y = h/2 - size[1]/2
    toplevel.geometry("%dx%d+%d+%d" % (size + (x, y)))

def callback(self):
    if tkinter.messagebox.askokcancel("Quit",
                                      "Do you want to leave?"):
        self.main.destroy()

def setResult(self, type, res):
    
    #calculated comments in vader analysis
    if (type == "neg"):
        self.negativeLabel.configure(text = 
                                     "you typed negative comment : "
                                     + str(res) + " % \n") 
    elif (type == "neu"):
        self.neutralLabel.configure( text = 
                                    "you typed  comment : "
                                    + str(res) + " % \n")
    elif (type == "pos"):
        self.positiveLabel.configure(text 
                                    = "you typed positive comment: "
                                     + str(res) + " % \n")
    

def runAnalysis(self):
    
    sentences = []
    sentences.append(self.line.get())
    sid = SentimentIntensityAnalyzer()
    
    for sentence in sentences:
        
        # print(sentence)
        ss = sid.polarity_scores(sentence)
        
        if ss['compound'] >= 0.05 : 
            self.normalLabel.configure(text = 
                                       " you typed positive statement: ") 

        elif ss['compound'] <= - 0.05 : 
            self.normalLabel.configure(text = 
                                       " you typed negative statement") 

        else : 
         self.normalLabel.configure(text = 
                                    " you normal typed  statement: ") 
        for k in sorted(ss):
            self.setResult(k, ss[k])
    print()
    

def editedText(self, event):
    self.typedText.configure(text = self.line.get() + event.char)
    

def runByEnter(self, event):
    self.runAnalysis()


def __init__(self):
    # Create main window
    self.main = Tk()
    self.main.title("Text Detector system")
    self.main.geometry("600x600")
    self.main.resizable(width=FALSE, height=FALSE)
    self.main.protocol("WM_DELETE_WINDOW", self.callback)
    self.main.focus()
    self.center(self.main)

    # addition item on window
    self.label1 = Label(text = "type a text here :")
    self.label1.pack()

    # Add a hidden button Enter
    self.line = Entry(self.main, width=70)
    self.line.pack()

    self.textLabel = Label(text = "\n",
                           font=("Helvetica", 15))
    self.textLabel.pack()
    self.typedText = Label(text = "", 
                           fg = "blue", 
                           font=("Helvetica", 20))
    self.typedText.pack()

    self.line.bind("<Key>",self.editedText)
    self.line.bind("<Return>",self.runByEnter)


    self.result = Label(text = "\n", 
                        font=("Helvetica", 15))
    self.result.pack()
    self.negativeLabel = Label(text = "", 
                               fg = "red",
                               font=("Helvetica", 20))
    self.negativeLabel.pack()
    self.neutralLabel  = Label(text = "",
                               font=("Helvetica", 20))
    self.neutralLabel.pack()
    self.positiveLabel = Label(text = "",
                               fg = "green",
                               font=("Helvetica", 20))
    self.positiveLabel.pack()
    self.normalLabel =Label (text ="",
                             fg ="red",
                             font=("Helvetica", 20))
    self.normalLabel.pack()

Driver code

myanalysis = analysis_text() mainloop()

`

Output:

text-detection-positivetext-detection-negative