How to use word2vec in gensim

share link

by Abdul Rawoof A R dot icon Updated: Oct 19, 2023

technology logo
technology logo

Solution Kit Solution Kit  

Word2Vec is a popular natural language processing (NLP) technique. It represents words as numerical vectors in a high-dimensional space. Tomas Mikolov and a team of researchers introduced it at Google in 2013. Word2Vec captures semantic relationships between words in text data. It's a fundamental tool for word embedding, which converts words into numerical vectors. It helps with various NLP tasks.  


Here are some examples of different types of data that can be input into a Word2Vec model:    

1. Text Data:   


  • Word2Vec helps with processing and learning embeddings from text data. It's used for text classification, sentiment analysis, and language modeling.   


2. Image Captions:   


  • Word2Vec helps to create embeddings for words in image captions, connecting textual descriptions.   


3. Time Series Data:   


  • In time series analysis, Word2Vec embeds time series data or sensor readings. It can help capture patterns and similarities between different time series.   


4. Graph Data:   


  • Word2Vec applies to graph data, like social networks. This helps to create embeddings for nodes or edges. This can be useful for tasks such as link prediction or community detection.    


5. Audio Data:  


  • In the case of speech processing, Word2Vec can transcribe spoken words. It can be used for speech recognition or speaker recognition.  


Here is an example of how to use wor2vec in gensim:

Fig: Preview the output you will get on running this code from your IDE.


In this solution, we are using the Gensim library.

import gensim as gensim

data = [['not', 'only', 'do', 'angles', 'make', 'joints', 'stronger', 'they', 'also', 'provide', 'more', 'consistent',
         'straight', 'corners', 'simpson', 'strongtie', 'offers', 'a', 'wide', 'variety', 'of', 'angles', 'in',
         'various', 'sizes', 'and', 'thicknesses', 'to', 'handle', 'lightduty', 'jobs', 'or', 'projects', 'where', 'a',
         'structural', 'connection', 'is', 'needed', 'some', 'can', 'be', 'bent', 'skewed', 'to', 'match', 'the',
         'project', 'for', 'outdoor', 'projects', 'or', 'those', 'where', 'moisture', 'is', 'present', 'use', 'our',
         'zmax', 'zinccoated', 'connectors', 'which', 'provide', 'extra', 'resistance', 'against', 'corrosion', 'look',
         'for', 'a', 'z', 'at', 'the', 'end', 'of', 'the', 'model', 'numberversatile', 'connector', 'for', 'various',
         'connections', 'and', 'home', 'repair', 'projectsstronger', 'than', 'angled', 'nailing', 'or', 'screw',
         'fastening', 'alonehelp', 'ensure', 'joints', 'are', 'consistently', 'straight', 'and', 'strongdimensions',
         'in', 'x', 'in', 'x', 'inmade', 'from', 'gauge', 'steelgalvanized', 'for', 'extra', 'corrosion',
         'resistanceinstall', 'with', 'd', 'common', 'nails', 'or', 'x', 'in', 'strongdrive', 'sd', 'screws']]

def word_vec_sim_sum(row):
    description = row
    description_embedding = gensim.models.Word2Vec([description], size=150,


[('do', 0.21456070244312286), ('our', 0.1713767945766449), ('can', 0.1561305820941925), ('repair', 0.14236785471439362), ('screw', 0.1322808712720871), ('offers', 0.13223429024219513), ('project', 0.11764446645975113), ('against', 0.08542445302009583), ('various', 0.08226475119590759), ('use', 0.08193354308605194)]


Follow the steps carefully to get the output easily.

  1. Install PyCharm Community Edition on your computer.
  2. Open the terminal and install the required libraries with the following commands.
  3. Install Gensim - pip install gensim.
  4. Create a new Python file(e.g.:
  5. Copy the snippet using the 'copy' button and paste it into that file(remove the output line at the end of the code).
  6. Run the file using the run button.


  1. In Gensim versions prior to 4.0.0, the size argument was used to specify the dimensionality of the word vectors. However, in Gensim 4.0.0 and later versions, this parameter has been renamed to vector_size. To fix the error, you should replace size with vector_size in our code.
  2. Starting from Gensim version 4.0.0, the iter parameter has been replaced with epochs.

I hope you found this useful. I have added the link to dependent libraries, and version information in the following sections.

I found this code snippet by searching for 'word not in vocabulary after training gensim word2vec model' in kandi. You can try any such use case!

Environment Tested

I tested this solution in the following versions. Be mindful of changes when working with other versions.

  1. The solution is created in PyCharm 2022.3.3.
  2. The solution is tested on Python 3.9.7.
  3. Gensim version 4.3.0.

Using this solution, we are able to use the word2vec function with simple steps. This process also facilitates an easy-to-use, hassle-free method to create a hands-on working version of code which would help us to use the word2vec function.

Dependent Library

gensimby RaRe-Technologies

Python doticonstar image 14417 doticonVersion:4.3.0doticon
License: Weak Copyleft (LGPL-2.1)

Topic Modelling for Humans


            gensimby RaRe-Technologies

            Python doticon star image 14417 doticonVersion:4.3.0doticon License: Weak Copyleft (LGPL-2.1)

            Topic Modelling for Humans

                      You can also search for any dependent libraries on kandi like 'Gensim'.


                      1. What is Gensim word2vec, and how does it relate to Natural Language Processing?  

                      Gensim Word2Vec is a popular Python library. It helps with word embedding and natural language processing (NLP) tasks. Word2Vec is a technique that transforms words or phrases into numerical vectors. It makes processing and analyzing textual data easier in ML and NLP applications.   

                      Here's how Gensim Word2Vec relates to NLP:    


                      • Word Embeddings: Word2Vec is a word embedding technique. It represents words as dense, continuous-valued vectors in a high-dimensional space. These vectors capture semantic relationships between words. For example, words with similar meanings or usages will have close vectors in this space.   
                      • Distributed Representation: It appears in similar contexts and should have similar vector representations. This fundamental NLP concept is often referred to as "distributional semantics". It allows NLP models to work with a more nuanced understanding of word meanings.   


                      2. How do Word Representations help with learning algorithms in Gensim word2vec?  

                      Here's how word representations help with learning algorithms in Gensim's Word2Vec:   

                      • Semantic Meaning Capture    
                      • Vector Arithmetic    
                      • Feature Learning   
                      • Reducing Dimensionality    
                      • Transfer Learning  


                      3. How can context be used to improve the accuracy of Gensim word2vec?  

                      Here are some ways to use context to improve the accuracy of Gensim Word2Vec:  

                      • Window Size   
                      • Training Data   
                      • Subsampling  
                      • Negative Sampling   
                      • Model Architecture   


                      4. What are word embeddings, and how do they work in Gensim word2vec?  

                      Word embeddings are vector representations of words in a continuous vector space. They are used in NLP to capture the semantic meaning of words. It is suitable for machine learning algorithms. Word embeddings have become a fundamental component of many NLP applications. They provide a way to represent words as dense, continuous-valued vectors. This acts as an input to various NLP models and algorithms.  


                      5. How effective is Document Classification using Gensim word2vec compared to other methods?  

                      Document classification using Gensim Word2Vec can be effective for certain tasks. Its effectiveness, compared to other methods depends on various factors. 


                      1. For any support on kandi solution kits, please use the chat
                      2. For further learning resources, visit the Open Weaver Community learning page.

                      See similar Kits and Libraries