Questions tagged [tf-idf]

In information retrieval, tf–idf, short for term frequency–inverse document frequency, is a numerical statistic that is intended to reflect how important a word is to a document in a collection or corpus.

Filter by
Sorted by
Tagged with
1 vote
0 answers
21 views

How to justify logarithmically scaled frequency for tf in tf-idf?

I am studying tf-idf (term frequency - inverse document frequency). The original logic for tf was straightforward: count of term t / number of total terms in the document. However, I came across the ...
user avatar
1 vote
1 answer
16 views

How to extract numerical features that can separate well documents belonging to two different classes?

I have a group of texts belonging to two different classes. I would like to extract numerical features that can separate well the two classes. Right now I implemented a classic TF-IDF with a document ...
user avatar
0 votes
0 answers
29 views

Unsupervised clustering with a categorical with tens of thousands of levels

I need to perform a clustering analysis of a medical claims dataset to identify anomalous healthcare providers. My dataset contains a variable called diagnosis code ...
user avatar
  • 549
0 votes
0 answers
29 views

Information Gain as a measure of term importance

I was watching the talk Beyond TF-IDF: Why, What and How. The speaker suggests replacing Inverse Document Frequency (IDF) with "Information Gain". Say we have a corpus of documents each ...
user avatar
  • 205
0 votes
0 answers
138 views

Is cosine similarity applicable for BM25 weighted vectors?

It seems to be very common to use cosine similarity for TF-IDF weighted vectors for comparison of documents and their retrieval. I am currently looking into the BM25 weighting scheme and here it seems ...
user avatar
0 votes
0 answers
9 views

Comparing Term Frequencies in Corpora of Different Sizes

Relatively new to quantitative linguistics and still trying to get a foothold on a solid methodology. I have two corpora: a "general use" American English corpus (enormous in size) and a ...
user avatar
0 votes
0 answers
10 views

IDF weighting convergence

I understand that TF-IDF weighting was discovered heuristically, but some research supports an information theoretic justification, too. My question is, how large of a corpus should you have before ...
user avatar
0 votes
0 answers
10 views

document subsimilarity matching

I'm looking to classify subsections of "full" documents based on their similarity to a set of subsections that have been manually curated and assigned labels (let's call these short ...
user avatar
  • 101
0 votes
1 answer
28 views

How do you use a TF-IDF matrix to score text similarity?

I'm trying to match strings of words with a website which has bulletpoints from all of the URL's I'm interested in whose text is most similar to it. The way I thought of doing it is to get all of the ...
user avatar
  • 121
1 vote
0 answers
56 views

Alternative to tf-idf for 2 documents?

I am currently trying to construct word clouds between two tidy text documents (tweets). My question is methodological, although I am using bind_tf_idf in R for the ...
user avatar
0 votes
1 answer
28 views

NLP - train a model

I have a large set of large texts (around 60K texts, each one having between 100 and 30K words). Each text has 5 corresponding values (the famous big5 traits). The task is the following: for a new ...
user avatar
0 votes
0 answers
37 views

Normalization on datasets with different distribution

I am having two datasets one is used for training a model and another one for testing it. The training dataset is large scale corpus of general context (parallel text) while the testing dataset ...
user avatar
  • 101
0 votes
1 answer
41 views

reducing overfitting does not improve performance

I'm training a multi-class classifier on text documents using a very classic (and somewhat old-fashioned) method on a data set consisting in relatively long text documents (average of 3000 tokens). ...
user avatar
0 votes
0 answers
23 views

NLP: vectorizer/metric to upweight absence of frequent terms

I'm doing hierarchical clustering of documents in a corpus; there are words that occur in almost all the documents. To define document similarity, I've used ...
user avatar
0 votes
1 answer
1k views

Calculating TF-IDF on a test set, having already built on training set

I have a need to engineer features from TF-IDF values for a downstream classification task. I (think) I have a reasonable grasp of TF-IDF as described in Sci-kit Learn documentation, but am unable to ...
user avatar
  • 213
0 votes
0 answers
21 views

Clustering mixed data based on text anlysis: Approach evaluation

As part of my project, I've been trying to analyse (and hopefully make some knowledgeable conclusions about) the movie database dataset, which consists of the following columns: Movie ID - ID of a ...
user avatar
0 votes
0 answers
25 views

Clustering mixed data based on text anlysis: Sparse Matrix problem

Good day/evening/any other time of the day! As part of my project, I've been trying to analyse (and hopefully make some konwlegable conclusions about) the movie database dataset, which consists of the ...
user avatar
0 votes
0 answers
89 views

SVM predicts always the same class

I have a dataset with tf-idf values and their corresponding classes and I am trying to do predictions using SVM. The problem is that all the results that it produces have the same class. Most related ...
user avatar
  • 3
1 vote
0 answers
1k views

What is the base of the `log` in tf-idf?

I have seen the wikipedia's document. For idf in this document, log10 is used. I have seen other examples of idf, using log base of e or ln. What is the difference? Is there any significant ...
user avatar
1 vote
1 answer
221 views

TF-IDF Calculation in Scikit Learn

...
user avatar
  • 180
-1 votes
1 answer
32 views

Recommender Engine for documents VS Search engine indexing

I have a lot of books and I want to make recommendations to users based on the description and the title of those books. I think that one way is to preprocess the content of the title and ...
user avatar
  • 109
1 vote
0 answers
408 views

PCA on TF-IDF matrix

I want to perform PCA on TF-IDF matrix, but I am not sure, should I center this matrix first or not? And should I do scaling or just centering?
user avatar
0 votes
1 answer
336 views

Why does TF-IDF use the count of the most common word in the document instead of total count of all words in the document?

From what I understand, the "term frequency" ("TF" in TF-IDF) is calculated from the number of times a certain term occurs in a document vs the most common term in a document: ...
user avatar
  • 187
1 vote
1 answer
1k views

How does adding/omitting lemmatization affect TF-IDF?

Lemmatization has some obvious benefits in TF-IDF, e.g. it decreases the vocabulary size. What are some other advantages, and what are some disadvantages to lemmatizing in the context of TF-IDF?
user avatar
2 votes
1 answer
1k views

How to calculate tf-idf for a single term

I am following the tf-idf method described in this paper: Measuring, Predicting and Visualizing Short-Term Change in Word Representation and Usage in VKontakte ...
user avatar
  • 592
2 votes
0 answers
79 views

Alternative to tf-idf with smaller penalty on previous usage

I am using tf-idf to find words that are particularly important to individual documents. This works pretty well for my purposes. However, one area where I feel like it isn't great is how harshly words ...
user avatar
  • 141
2 votes
2 answers
501 views

Applying TF/IDF to non-text data?

I have a classification problem in which I am supposed to predict the end state of an object based on a set of events it experiences. There are about one thousand possible events and each object is ...
user avatar
  • 61
2 votes
2 answers
7k views

Determining epsilon for DBSCAN

I'm using the method described in this paper for determining the optimal epsilon value for DBSCAN clustering in which a plot of the nearest neighbors is used: However, the plots in the paper and ...
user avatar
0 votes
1 answer
24 views

Did my text data come from two distinct distributions?

I have labeled text data from two different classes. I have calculated tfidf feature representation of all the sentences in question. I have a huge matrix where rows are sentences and columns are ...
user avatar
0 votes
1 answer
360 views

High Precision and low recall score for TF-IDF when using KNN algorithm

I have twitter data which is labelled with the sentiment(Postive, Negative, Neutral) and I have evaluated the performance of Tf-Idf and Doc2Vec feature extractor using the KNN algorithm and logistic ...
user avatar
1 vote
1 answer
436 views

Correct algorithm for string classification

I have a long list of DNA strings (of equal length) made of 4 letters (A,T,G,C). I want to do a binary classification on the strings. I have two basic quetsions: I have a lot of duplicate strings ...
user avatar
1 vote
0 answers
203 views

Clustering algorithms for multiple features that are arrays/lists

my issue is that I want to cluster data from a specific context. The dataset was 3 different texts that cannot be concatenated. Now I have the following "data-object" in Python: It is an array with ...
user avatar
  • 11
0 votes
0 answers
218 views

What is the maximum number of features in Logistic Regression Problem

I was doing Text classification(binary) hosted on kaggle with approx 1.3 millions observations. My approach is to use Logistic Regression after computing the TF-IDF matrix with n-grams = 1:3. With ...
user avatar
0 votes
1 answer
555 views

Negative values in word vectorizations

I am currently in the middle of reading Applied Text Analysis with Python by Bengfort, Bilbro, and Ojeda, and encountered a sentence that I've struggled to wrap my head around. In the section ...
user avatar
  • 231
2 votes
1 answer
425 views

TF-IDF String to Vector Weka bias

For example, let's say I have a text dataset like: "words text etc",label "words text etc",label "words text etc",label If I ...
user avatar
1 vote
1 answer
2k views

How to combine two tfidf sparse vectors

Say that I have two document collections that I have created a tf-idf sparse vector for each one using TfidfVectorizer. How could I combine those two vectors into one that would resemble the tfidf of ...
user avatar
3 votes
1 answer
1k views

Tf-idf for text classification: On what should IDF be calculated?

The TF-IDF value of a word specifies how important a word for each document is. My setting is any text classification where one has multiple documents of with different classes: Let's take a lot of ...
user avatar
  • 71
1 vote
0 answers
583 views

Practically speaking, is the TF-IDF threshold universal across different corpus?

I would like to know the practical threshold of the TF-IDF (just like the practical p-value cutoff of 0.1 or 0.05 in hypothesis tests). I tried to look at it in some previous post, and some people ...
user avatar
  • 133
3 votes
0 answers
392 views

Delta TF-IDF right choice for multi classification problem

In the paper of Martineau & Finin they describe their new approach with Delta TF-IDF . Instead of measuring how rare features are in the document, they weight these values by how biased they are ...
user avatar
  • 81
1 vote
0 answers
300 views

Why is the size of fitted truncated svd model is so big?

I have a dataset with tfidf matrix of shape (200000, 565000). I am fitting truncated svd of 500 dimensions from sklearn onto it and pickling the resulting svd object for later use. The pickle file is ...
user avatar
  • 11
0 votes
1 answer
3k views

How to improve performance for LDA?

I am running LDA on health-related data. Specifically I have ~500 documents that contain interviews that last around 5-7 pages. Other than that, I cannot really go into the details of the data due to ...
user avatar
2 votes
1 answer
4k views

TF-IDF vs just TF in text classification [duplicate]

It's common to see people using a tf-idf representation of words for text classification, but I don't understand why not just use tf. Say $tf(t,d)$ is the $tf$ of term $t$ in a document $d$ and $idf(...
user avatar
  • 479
1 vote
0 answers
447 views

Text classification using tf idf

I am developing a text classification model. At this moment I have to classify some documents in six different classes. I am using a simple approach as a starting point based on random forests over a ...
user avatar
  • 203
0 votes
1 answer
341 views

Using k fold cross validation gives lower results than without using it

I have implemented text classification in the sentence level by following through this tutorial. I have used tf-idf and NB & SVM as shown in the tutorial. The code is working fine with my dataset. ...
user avatar
1 vote
0 answers
124 views

How to compute tf-idf for sequential k means?

I am trying to run the sequential K means algorithm as described here on a corpus using tf-idf as a vectorized representation of my documents. I do this because I don't have access to all of my ...
user avatar
0 votes
2 answers
578 views

Use tf-idf for QnA

I have a corpora of queries and answers where the queries are the title of different documents and the answers are a short description of them. E.g: Title: African Civilian Deaths Description:...
user avatar
  • 101
0 votes
0 answers
1k views

Accuracy increases on decreasing the percentage of training data with stable precision, recall and F-score

I am currently working on a classification problem using tf-idf and Naive Bayes for two classes A and B. I have randomly shuffle the dataset before implementation, and I was experimenting with the ...
user avatar
1 vote
0 answers
92 views

TF-IDF on a sub-corpus

I'm analyzing newspaper articles, some are 2 or 3 pages long, some a few lines long. My Corpus is made of a few thousands of dated articles spanning over a few ...
user avatar
2 votes
1 answer
4k views

How does correlation work in text mining?

When we are done in pre-processing the text (removing stop words, stemming, lower case) then creating a term document that has TF-IDF as weight. How can I decide what correlation test to do between ...
user avatar
  • 167
5 votes
1 answer
5k views

What does word embedding weighted by tf-idf mean?

The paper that I am reading explains about how it implemented the feature vector used for a twitter sentiment classification task. The first is a simple combination, where each tweet is represented ...
user avatar
  • 51