Gist 751982c1e21147b124a9b6d5fde96a4e

100%

Gist 751982c1e21147b124a9b6d5fde96a4e

✓ Published0🌍 Public

Last edited Dec 29, 2021

Created on Dec 29, 2021

The visualization examines sponsored content in a social media dataset by processing raw captions through a custom pipeline. It uses Python’s `re` module to strip emojis and punctuation, then applies spaCy’s named entity recognition to extract organizations and products into a "Sponsor" list, while also capturing tags via string matching. The code builds a DataFrame with `pandas`, adding a binary "Sponsored" column based on whether either field is non-empty. It highlights the detection of promotional mentions by combining entity-based and rule-based tagging, ultimately displaying cleaned captions alongside the derived sponsorship metadata.

AI-generated description

Similar vizzes

Loading thumbnail…

Gist e14e45693dae94f60b953c09a641f6a4

This example shows a data-processing pipeline that identifies and extracts potential sponsor names and tags from caption text. It classifies each row as “Yes” or “No” for sponsorship based on whether any sponsor or tag tokens are present. The code uses Python’s `re` module for emoji removal and text cleaning, and relies on spaCy’s named entity recognition (via `list_words.ents`) to detect organizations and products. It applies custom string-manipulation functions like `remove_emoji`, `pairList`, and `getTag` to filter and deduplicate extracted entities, then combines sponsor and tag columns before checking for non-empty results.

AArizonaTay

85% match

Loading thumbnail…

Gist dec05c8e23491da95f80ba891c35100a

This example trains a custom named entity recognition (NER) model using spaCy to identify sponsor mentions, product names, and promo codes in social media captions. It first preprocesses a data frame of captions by stripping non-alphabetic characters, then initializes a pre-trained English model and adds custom labels. Training uses 10 epochs with minibatch compounding and dropout, iterating over hand-labeled examples that mark entity spans. After training, the model is saved to disk and reloaded to test inference on new text, demonstrating the pipeline’s ability to extract promotional entities from informal, hashtag-heavy captions.

AArizonaTay

75% match

Loading thumbnail…

Gist 55fc864ec9cea1107845d3ed7a3dab8b

This example demonstrates a text-cleaning pipeline for caption data, showing how raw captions are converted into tokenized, filtered lists for downstream analysis. The visualization itself is not rendered; instead, the focus is on the data preprocessing logic. The code uses `pandas` with `apply` to run natural language processing via `spaCy` (`nlp`), extracting tokens from the `Caption` column. It then applies a custom `tokens` function that removes stop words and non-alphanumeric characters using `re.match`, while preserving tokens containing "@" symbols. The result is a new `clean_caption` column, highlighting a common step in text mining workflows.

AArizonaTay

73% match

Loading thumbnail…

Gist 6437893f183d99e863d835425ffa46f8

This example visualizes the distribution of tokenized caption text from a dataset of images, showing how frequently each word appears after cleaning. The visualization displays the processed terms as a bar chart or word cloud, with the data derived from the `Caption` field of the input dataframe. The preprocessing pipeline loads the `en_core_web_lg` spaCy model to tokenize each caption, removes English stop words and non-alphanumeric characters, and converts all terms to lowercase. The code relies on the `spacy` library for linguistic analysis and standard Python regex operations via the `re` module to filter tokens, while the `stopwords` set comes from NLTK.

AArizonaTay

70% match

Loading thumbnail…

Gist da5f7a5f8cf01b0874d92349b33ec806

This visualization uses a Latent Dirichlet Allocation (LDA) topic model to classify Instagram captions into eight thematic categories, such as Giveaway, Fitness, and Love. It first shows the derived topics with their top ten keywords per topic, then assigns each caption its dominant topic and displays a random sample of the resulting annotations. The analysis relies on the Gensim library for the LDA model and coherence scoring, while Pandas DataFrames and the Dictionary and doc2bow APIs handle text preprocessing and corpus construction. A custom function maps each caption’s topic distribution to its most likely label, and the final output presents a sample of the enriched data with the assigned topic column.

AArizonaTay

69% match

Loading thumbnail…

Gist 0d66893f89c8190de7c21268dfeef1d1

The visualization explores sponsored Instagram posts, showing how engagement rates and posting frequency vary by hour of the day. Two line charts, built with Plotly Express and Plotly Graph Objects, reveal a peak in average engagement at 4pm and the highest number of posts at noon. A separate horizontal bar chart, also using Plotly, ranks the top 20 brand collaborators by counting how often each sponsor appears in the filtered dataset, which only includes posts marked as "Sponsored." The code groups timestamps by hour and processes sponsor tags by stripping "@" symbols to tally frequencies.

AArizonaTay

68% match

Loading thumbnail…

Gist 95ca610ee079b0bdb562a98f57c792f4

The visualization displays the top 20 brands that collaborate with influencers, ranked by the frequency of their appearances in a dataset. It highlights which sponsors are most commonly associated with influencer posts, providing a clear view of brand partnership patterns. The chart is a horizontal bar plot generated using Plotly Express, with the `px.bar` function called on a sorted dataframe. The code processes the data by iterating through sponsored entries, cleaning sponsor names, and aggregating counts via `groupby` and `reset_index`. The final plot is styled with a title and centered axis labels, relying on Pandas for data manipulation.

AArizonaTay

68% match

Loading thumbnail…

Gist ba350b90fcee35acc38ff961c4eec95a

Two horizontal bar charts display the percentage of sponsored posts by industry and by country, using Plotly Express’s `px.bar` after grouping data with pandas `groupby` and `apply`. Each chart sorts its top 20 categories descending by sponsored share, with the industry chart titled “Sponsored Post(%) by Industry” and the country chart “Sponsored Post(%) by Country.” The code computes sponsored counts per category from the `inf_df` DataFrame, merges sponsored and non-sponsored totals, then calculates percentages for visualization. The source data appears to originate from a dataset of influencer posts, with plots rendered as static, interactive HTML figures.

AArizonaTay

67% match