Imports System
Imports System.Collections.Generic
Module KeywordMatching
'
' Tokenize text into words.
' - Keeps only letters and digits
' - Splits on punctuation and spaces
'
Function Tokenize(text As String) As HashSet(Of String)
Dim words As New HashSet(Of String)()
Dim word As String = ""
For Each c As Char In text
If Char.IsLetterOrDigit(c) Then
word &= Char.ToLower(c)
ElseIf word.Length > 0 Then
words.Add(word)
word = ""
End If
Next
If word.Length > 0 Then
words.Add(word)
End If
Return words
End Function
'
' // Find keyword matches across THREE OR MORE texts
' // -------------------------------------------------------------
' This function receives a list of sets.
' It returns the intersection of ALL sets.
'
Function FindMatchesMultiple(allSets As List(Of HashSet(Of String))) As HashSet(Of String)
If allSets.Count = 0 Then
Return New HashSet(Of String)()
End If
' Start with the first set
Dim result As New HashSet(Of String)(allSets(0))
' Intersect with each remaining set
For i As Integer = 1 To allSets.Count - 1
Dim temp As New HashSet(Of String)()
For Each w As String In result
If allSets(i).Contains(w) Then
temp.Add(w)
End If
Next
result = temp
Next
Return result
End Function
Sub Main()
' -------------------------------------------------------------
' Three text blocks to compare
' -------------------------------------------------------------
Dim text1 As String =
"Machine learning allows computers to learn from data. " &
"It is widely used in modern applications."
Dim text2 As String =
"Data science uses machine learning techniques. " &
"Applications rely on data-driven models."
Dim text3 As String =
"Modern applications of machine learning include data analysis, " &
"automation, and intelligent systems."
' -------------------------------------------------------------
' Tokenize all texts
' -------------------------------------------------------------
Dim words1 = Tokenize(text1)
Dim words2 = Tokenize(text2)
Dim words3 = Tokenize(text3)
' Put them into a list for multi-text comparison
Dim allSets As New List(Of HashSet(Of String)) From {words1, words2, words3}
' -------------------------------------------------------------
' Find keyword matches across ALL texts
' -------------------------------------------------------------
Dim matches = FindMatchesMultiple(allSets)
' -------------------------------------------------------------
' Output results
' -------------------------------------------------------------
Console.WriteLine("Matched Keywords Across ALL Texts:")
For Each w As String In matches
Console.Write(w & " ")
Next
Console.WriteLine()
End Sub
End Module
'
' run:
'
' Matched Keywords Across ALL Texts:
' applications data learning machine
'
