sentiment analysis

Single-Module Pipeline: `sentiment`

This document is a walkthrough of how to assemble and use a single-module pipeline that only includes a sentiment module.

Sentiment analysis is used to determine the emotional tone of a body of text—to what extent it's positive, negative, and neutral. Its applications include gauging public opinion on social media, enhancing customer service through feedback analysis, monitoring brand reputation, and improving marketing strategies by understanding consumer sentiments.

The document is divided into the following sections:

Pipeline Setup
Required Input Format
Using the Default Model
Using a Non-Default Model

Pipeline Setup

Let's first instantiate a single-module sentiment pipeline.

We use the create_pipeline method for this, passing only the sentiment module name into module_chain.

# create a pipeline with a single sentiment module
pipeline = krixik.create_pipeline(name="single_sentiment_1", module_chain=["sentiment"])

Required Input Format

The sentiment module accepts JSON file input. The input JSON must respect this format.

Let's take a quick look at a valid input file, and then process it.

# examine contents of a valid input file
with open(data_dir + "input/valid.json") as f:
    print(json.dumps(json.load(f), indent=2))

[
  {
    "snippet": "I love this movie and i would watch it again and again!"
  },
  {
    "snippet": "Operating profit totaled EUR 9.4 mn, down from EUR 11.7 mn in 2004."
  }
]

Using the Default Model

Let's process our test input file using the sentiment module's default model: distilbert-base-uncased-finetuned-sst-2-english.

Given that this is the default model, we need not specify model selection through the optional modules argument in the process method.

# process the file with the default model
process_output = pipeline.process(
    local_file_path=data_dir + "input/valid.json",  # the initial local filepath where the input file is stored
    local_save_directory=data_dir + "output",  # the local directory that the output file will be saved to
    expire_time=60 * 30,  # process data will be deleted from the Krixik system in 30 minutes
    wait_for_process=True,  # wait for process to complete before returning IDE control to user
    verbose=False,
)  # do not display process update printouts upon running code

The output of this process is printed below. To learn more about each component of the output, review documentation for the process method.

Because the output of this particular module-model pair is a JSON file, the process output is provided in this object as well (this is only the case for JSON outputs). Moreover, the output file itself has been saved to the location noted in the process_output_files key. The file_id of the processed input is used as a filename prefix for the output file.

# nicely print the output of this process
print(json.dumps(process_output, indent=2))

{
  "status_code": 200,
  "pipeline": "single_sentiment_1",
  "request_id": "c83bf64d-11c4-4e23-b3ad-26e126596b54",
  "file_id": "b29385f1-b570-4ad6-b6a4-70ddff919a32",
  "message": "SUCCESS - output fetched for file_id b29385f1-b570-4ad6-b6a4-70ddff919a32.Output saved to location(s) listed in process_output_files.",
  "warnings": [],
  "process_output": [
    {
      "snippet": "I love this movie and i would watch it again and again!",
      "positive": 1.0,
      "negative": 0.0,
      "neutral": 0.0
    },
    {
      "snippet": "Operating profit totaled EUR 9.4 mn, down from EUR 11.7 mn in 2004.",
      "positive": 0.021,
      "negative": 0.979,
      "neutral": 0.0
    }
  ],
  "process_output_files": [
    "../../../data/output/b29385f1-b570-4ad6-b6a4-70ddff919a32.json"
  ]
}

To confirm that everything went as it should have, let's load in the text file output from process_output_files:

# load in process output from file
with open(process_output["process_output_files"][0]) as f:
    print(json.dumps(json.load(f), indent=2))

[
  {
    "snippet": "I love this movie and i would watch it again and again!",
    "positive": 1.0,
    "negative": 0.0,
    "neutral": 0.0
  },
  {
    "snippet": "Operating profit totaled EUR 9.4 mn, down from EUR 11.7 mn in 2004.",
    "positive": 0.021,
    "negative": 0.979,
    "neutral": 0.0
  }
]

Using a Non-Default Model

To use a non-default model like distilbert-base-multilingual-cased-sentiments-student, we must enter it explicitly through the modules argument when invoking the process method.

# process the file with a non-default model
process_output = pipeline.process(
    local_file_path=data_dir + "input/valid.json",  # all arguments save for modules are as above
    local_save_directory=data_dir + "output",
    expire_time=60 * 30,
    wait_for_process=True,
    verbose=False,
    modules={"sentiment": {"model": "distilbert-base-multilingual-cased-sentiments-student"}},
)  # specify a non-default model for this process

The output of this process is printed below.