PUBLISH

We are pleased to announce the launch of a new website for <a href="https://lab.publishprotocol.io/" rel="noopener noreferrer nofollow">PUBLISHlab</a>, our in-house media innovation laboratory that explores how emerging technologies can be used to help news organizations combat misinformation, increase engagement, and boost income.Built in <a href="https://flask.palletsprojects.com/" rel="noopener noreferrer nofollow">Flask</a>, the website features number of prototypes that make use of and adapt existing technologies in the name of journalism.These include a content recommender, a sentiment analysis tool, an automatic image tagger, and a publish-to-blockchain tool.Content recommenderThis prototype automatically suggests related news content. The prototype takes in one or more news feeds, which are then parsed using <a href="https://universal-feedparser.readthedocs.io/" rel="noopener noreferrer nofollow">Universal Feed Parser</a> and converted to a <a href="https://pandas.pydata.org/" rel="noopener noreferrer nofollow">pandas</a> dataframe. It then extracts a headline from a randomly selected news story and performs NER (named entity recognition) using a natural language processing library called <a href="https://spacy.io/" rel="noopener noreferrer nofollow">spaCy</a>and the <a href="https://spacy.io/models/en#en_core_web_sm" rel="noopener noreferrer nofollow">en-core-sm</a> english language model. NER is the task of identifying named entities, such as people, places, and organizations, in a given text. Finally, it uses the <a href="https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html" rel="noopener noreferrer nofollow">CountVectorizer</a> class and <a href="https://scikit-learn.org/stable/modules/generated/sklearn.metrics.pairwise.cosine_similarity.html" rel="noopener noreferrer nofollow">cosine_similarity</a> method of a machine learning library called <a href="https://scikit-learn.org/" rel="noopener noreferrer nofollow">sci-kit learn</a> to create a document-term matrix and identify similar headlines.Sentiment analysis toolThis prototype assigns a sentiment score to a text based on how positive or negative it is. As a pre-processing step, it identifies the predominant language of a user inputted text and, if needed, translates it to English using the <a href="https://pypi.org/project/googletrans/" rel="noopener noreferrer nofollow">googletrans</a> python library. The text is then analyzed using <a href="https://github.com/cjhutto/vaderSentiment" rel="noopener noreferrer nofollow">VADER-Sentiment-Analysis</a>, which looks for various text features such as negations, exclamation marks, all caps, degree modifiers, sentiment-laden slang, and UTF-8 encoded emojis. A sentiment score is then assigned at both the text and sentence level. Finally, sentences are color-coded to visually convey the sentiment score. The technology could be used to identify positive and negative news comments and product reviews.Automatic image taggerThis prototype automatically tags images using a deep learning image model. When a user uploads an image, the image is pre-processed (e.g., resized and cropped) using PyTorch, a popular python-based machine learning library often used in computer vision projects. The image is then run against a computer vision model. Currently, the only available option is ResNet-50, a general computer vision model based on ImageNet. The prototype then returns the top 5 labels along with their confidence scores. The technology could be used within a content hub to make images searchable.Publish-to-blockchain toolThis prototype indexes news content on the EOSIO blockchain. It takes a news story and converts it to a blockchain and news media friendly format derived from <a href="https://iptc.org/standards/ninjs/" rel="noopener noreferrer nofollow">ninjs</a> (News in JSON). The resulting JSON object is then published as part of a blockchain transaction on the <a href="https://jungletestnet.io/" rel="noopener noreferrer nofollow">Jungle Testnet</a> (a popular EOSIO testnet). If desired, the content can be encrypted using a SHA-256 hashing algorithm before pushing the transaction. The technology has a number of potential use cases, including to protect copyright, increase journalistic transparency, and safeguard content from data loss and censorship.Outside of these four prototypes, PUBLISHlab is also working on using transfer learning to build more accurate computer vision models, news automation, and news summarization.

PUBLISHlab launches website to showcase prototypes

PUBLISH

Další články publikované 30. 3. 2023

The Flare Time Series Oracle (FTSO) Ready to Serve Smart Contracts and dApps

Sharia-Compliant Cryptocurrencies: A Pathway to Inclusive Islamic Economic Growth

The most common types of MEV and protection from toxic strategies

Kraken Reaffirms Commitment to Canada, Files Pre-Registration With OSC

PUBLISH awarded highly esteemed BBB rating in recent Xangle Credibility Ratings report

European Union Adopts New Regulations to Prevent Crypto-Based Money Laundering

Join our free newsletter for daily crypto updates!