Hubly FAQs & knowledge base

Hubly is a game changing app platform that enables you to quickly create online communications hubs (or communities) that are constantly monitored by 'Hubshield' our AI which prevents harmful content from being uploaded. Once you have created a Hub you can post safe content, chat with hub messaging and topics, create group video and voice calls, organise events, share calendars, store and share files, manage subscriptions. Once you've uploaded some content you can then invite who you want to view, collaborate and share and if you want to turn your hub into a business even charge them for membership. Safer communication Hubs can be created for anything... Businesses, Brands, Influencers, Communication, Onboarding, Shops, Focus groups, Teams, Societies, Universities, Schools, Sports and social Clubs etc

A Hub is what we call an online community or group, but it's much more than that. Creating a Hub with Hubly also enables you to connect to any existing apps or services and to receive, display and send data (which is displayed on a personalised member dashboard), therefore streamlining your communications into one central place for your members or employees. Creating a Hub using Hubly enables you to... Post content including posts to you the activity feed, create articles and publish pages. You can also share In hub messages and create popular topic channels, video chat, use shared calendars, manage files, store and share files, manage subscriptions and much more... You can also then invite who you want to become members of your community Hub so they can view content, collaborate and share and if you want to turn your community Hub into a business you can even charge them for membership and become a Hub millionaire...

You can create a hub for anything... Brands, Businesses, Influencers, Communication, Onboarding, Sport, Brands, Shops, Focus groups, Teams, Societies, Universities, Schools, Clubs, Projects, Families, Individuals or whatever else is relevant or makes sense to you.

When you are invited to become a member of a community hub, Hubly automatically creates a Personal hub for you to use should you want it. A personal hub is totally unique as by default it’s not listed on the internet. This gives it an extra level of privacy. Of course, if you like you can choose to list it on the internet and then it will become discoverable by anyone, although no one can become a member unless you choose to accept them. Post content… You can quickly and easily post and upload content to your personal hub and style it the way you want Link to your social accounts… Your personal Hub can quickly be linked to view and monitor all your existing social media feeds like Twitter, Facebook, LinkedIn, Tictoc, Instagram etc. Protection from harmful content… Once you’ve linked your existing social media accounts, Hubly will work its magic to protect you from any potentially abusive content. It’s your choice… If you don’t want Hubly to protect you you can choose to switch it off at any time. Invite your friends… You can easily invite and chat to your friends. Complete Privacy Unlike the Public hubs you can see on Hubly. Personal hubs are not discoverable on Hubly or displayed the Internet. This means the only people who will ever have access to them are you and any friends you choose to invite. This makes them much more private and secure. Who can benefit from using a Personal hub? Personal secure private Hubs can be created for individuals especially those in the public eye (Sports and TV personalities, MP’s, Public figures etc). These hubs can quickly be linked to view and monitor popular and personal social media feeds like Twitter, Facebook, LinkedIn, Tictoc, Instagram etc.

Personal secure private Hubs can be created for individuals especially those in the public eye (Sports and TV personalities, MP’s, Public figures etc). These hubs can quickly be linked to view and monitor popular and personal social media feeds like X (formally known as Twitter), Facebook, LinkedIn, Tiktok, Instagram etc. Once Hubshield AI will then scan the content and reject anything that is harmful offensive.

Your Website is a public facing place for new and existing customers who already know your business, whereas a Hubly (or a Hub) is a place where you invite members and can attract and engage with new people or customers.

Yes you do. But we reserve the right to use the data gathered to provide you with useful Hub Insights and reporting etc. These insights are valuable when growing a hub community and also provide the opportunity to reward community members for the data gathered.

Yes. There are multiple settings for member contributors, managers, admin. Go to your Members page and you can change any member to allow them more access to manage and contribute to you Hub.

Yes you can do this easily. 1. Transferring a community yourself Just create your hub and start uploading and publishing your content. If you have a-lot of members and you want to invite everyone to your new hub community in one go, you will need to find and export (or create) a list of their email addresses and or mobile phone numbers. Once done you will be able to access the bulk invite option and invite everyone in one go. Each member will receive an email and or text with a link inviting them to you new hub. From there they just need to click on the links and follow the instructions 2. Getting the Hubly onboarding team to do it for you For Brands, Businesses and organisations who have large communities you may find it easier to get our specialist onboarding team to handle this for you. To do this just contact us and we'll call you back to discuss your requirements.

All community hubs are set 'by default' to require people to apply for membership and can only become members once the Hub owners or Administrators accept. This is a popular option for hub owners who want to review their members before they join. Auto accept members - Should you want to, you can also set your hub so you can automatically accept members without having to review and accept them manually. Examples of this type of hub are hub owners who want to grow their hub membership quickly and are happy to welcome anyone into their community.

Brand hub communities are used to gain valuable customer feedback and useful insights. You can create a public or private brand hubs.

A public hub - Anyone can search for this type of hub, see this listed and apply to join. This is for brands that want to advertise their hubs and increase their membership. A private hub - This type of hub is hidden from sight and cannot be found listed on search engines. It is invite only and can only be searched for and found by members. Typical hubs like this include hubs created for internal communication use only e.g Business hubs. Departments, Projects, Family etc.

Personal attacks are a form of abuse detected by Hubly - Hubshield. Every instance scanned and detected is logged as an instance of abuse. Personal attacks also cover cyberbullying. A personal attack is defined as: An attack on a person who is a party to the conversation; addressing in second person (“you”) clearly means it’s the case but in order to recognise nicknames and other participants, a list of participants must be submitted. It is not an attack on a social group (ethnicity, religious group, racial minority, etc.). These kind of attacks are assigned the group 'bigotry'.

Personal attacks are a form of abuse detected by Hubly - Hubshield. Every instance is logged as an instance of abuse Personal attacks also cover Cyberbullying. Note that a personal attack is: An attack on a person who is a party to the conversation; addressing in second person (“you”) clearly means it’s the case but in order to recognise nicknames and other participants, a list of participants must be submitted. Not an attack on a social group (ethnicity, religious group, racial minority, etc.). Such attacks are assigned the type bigotry.

Hubly - Sentiment analysis Sentiment analysis (or opinion mining) is a natural language processing (NLP) technique used to determine whether data is positive, negative or neutral. Sentiment analysis is often performed on textual data to help businesses monitor brand and product sentiment in customer feedback, and understand customer needs. Sentiment analysis is simply categorised as the following: Positive Negative Neutral Mixed Types of Sentiment Analysis Sentiment analysis focuses on the polarity of a text (positive, negative, neutral) but it also goes beyond polarity to detect specific feelings and emotions (angry, happy, sad, etc), urgency (urgent, not urgent) and even intentions (interested v. not interested). Depending on how you want to interpret customer feedback and queries, you can define and tailor your categories to meet your sentiment analysis needs. In the meantime, here are some of the most popular types of sentiment analysis: Graded Sentiment Analysis If polarity precision is important to your business, you might consider expanding your polarity categories to include different levels of positive and negative: Very positive Positive Neutral Negative Very negative This is usually referred to as graded or fine-grained sentiment analysis, and could be used to interpret 5-star ratings in a review, for example: Very Positive = 5 stars Very Negative = 1 star Emotion detection Emotion detection sentiment analysis allows you to go beyond polarity to detect emotions, like happiness, frustration, anger, and sadness. Many emotion detection systems use lexicons (i.e. lists of words and the emotions they convey) or complex machine learning algorithms. One of the downsides of using lexicons is that people express emotions in different ways. Some words that typically express anger, like bad or kill (e.g. your product is so bad or your customer support is killing me) might also express happiness (e.g. this is bad ass or you are killing it). Aspect-based Sentiment Analysis Usually, when analysing sentiments of texts you’ll want to know which particular aspects or features people are mentioning in a positive, neutral, or negative way. That's where aspect-based sentiment analysis can help, for example in this product review: "The battery life of this camera is too short", an aspect-based classifier would be able to determine that the sentence expresses a negative opinion about the battery life of the product in question. Multilingual sentiment analysis Multilingual sentiment analysis can be difficult. It involves a lot of preprocessing and resources. Most of these resources are available online (e.g. sentiment lexicons), while others need to be created (e.g. translated corpora or noise detection algorithms), but you’ll need to know how to code to use them. Alternatively, you could detect language in texts automatically with a language classifier, then train a custom sentiment analysis model to classify texts in the language of your choice.

Sentiment analysis, otherwise known as opinion mining, works thanks to natural language processing (NLP) and machine learning algorithms, to automatically determine the emotional tone behind online conversations. There are different algorithms you can implement in sentiment analysis models, depending on how much data you need to analyse, and how accurate you need your model to be. We’ll go over some of these in more detail, below. Sentiment analysis algorithms fall into one of three buckets: Rule-based: these systems automatically perform sentiment analysis based on a set of manually crafted rules. Automatic: systems rely on machine learning techniques to learn from data. Hybrid systems combine both rule-based and automatic approaches. Rule-based Approaches Usually, a rule-based system uses a set of human-crafted rules to help identify subjectivity, polarity, or the subject of an opinion. These rules may include various NLP techniques developed in computational linguistics, such as: Stemming, tokenisation, part-of-speech tagging and parsing. Lexicons (i.e. lists of words and expressions). Here’s a basic example of how a rule-based system works: Defines two lists of polarised words (e.g. negative words such as bad, worst, ugly, etc and positive words such as good, best, beautiful, etc). Counts the number of positive and negative words that appear in a given text. If the number of positive word appearances is greater than the number of negative word appearances, the system returns a positive sentiment, and vice versa. If the numbers are even, the system will return a neutral sentiment. Rule-based systems are very naive since they don't take into account how words are combined in a sequence. Of course, more advanced processing techniques can be used, and new rules added to support new expressions and vocabulary. However, adding new rules may affect previous results, and the whole system can get very complex. Since rule-based systems often require fine-tuning and maintenance, they’ll also need regular investments. Automatic Approaches Automatic methods, contrary to rule-based systems, don't rely on manually crafted rules, but on machine learning techniques. A sentiment analysis task is usually modelled as a classification problem, whereby a classifier is fed a text and returns a category, e.g. positive, negative, or neutral. The Training and Prediction Processes In the training process (a), our model learns to associate a particular input (i.e. a text) to the corresponding output (tag) based on the test samples used for training. The feature extractor transfers the text input into a feature vector. Pairs of feature vectors and tags (e.g. positive, negative, or neutral) are fed into the machine learning algorithm to generate a model. In the prediction process (b), the feature extractor is used to transform unseen text inputs into feature vectors. These feature vectors are then fed into the model, which generates predicted tags (again, positive, negative, or neutral). Feature Extraction from Text The first step in a machine learning text classifier is to transform the text extraction or text vectorisation, and the classical approach has been bag-of-words or bag-of-ngrams with their frequency. More recently, new feature extraction techniques have been applied based on word embeddings (also known as word vectors). This kind of representations makes it possible for words with similar meaning to have a similar representation, which can improve the performance of classifiers. Classification Algorithms The classification step usually involves a statistical model like Naïve Bayes, Logistic Regression, Support Vector Machines, or Neural Networks: Naïve Bayes: a family of probabilistic algorithms that uses Bayes’s Theorem to predict the category of a text. Linear Regression: a very well-known algorithm in statistics used to predict some value (Y) given a set of features (X). Support Vector Machines: a non-probabilistic model which uses a representation of text examples as points in a multidimensional space. Examples of different categories (sentiments) are mapped to distinct regions within that space. Then, new texts are assigned a category based on similarities with existing texts and the regions they’re mapped to. Deep Learning: a diverse set of algorithms that attempt to mimic the human brain, by employing artificial neural networks to process data. Hybrid Approaches Hybrid systems combine the desirable elements of rule-based and automatic techniques into one system. One huge benefit of these systems is that results are often more accurate. Sentiment Analysis Challenges Sentiment analysis is one of the hardest tasks in natural language processing because even humans struggle to analyse sentiments accurately. Data scientists are getting better at creating more accurate sentiment classifiers, but there’s still a long way to go. Let’s take a closer look at some of the main challenges of machine-based sentiment analysis: Subjectivity & Tone Context & Polarity Irony & Sarcasm Comparisons Emojis Defining Neutral Human Annotator Accuracy Subjectivity and Tone There are two types of text: subjective and objective. Objective texts do not contain explicit sentiments, whereas subjective texts do. Say, for example, you intend to analyse the sentiment of the following two texts: The package is nice. The package is red. Most people would say that sentiment is positive for the first one and neutral for the second one, right? All predicates (adjectives, verbs, and some nouns) should not be treated the same with respect to how they create sentiment. In the examples above, nice is more subjective than red. Context and Polarity All utterances are uttered at some point in time, in some place, by and to some people, you get the point. All utterances are uttered in context. Analysing sentiment without context gets pretty difficult. However, machines cannot learn about contexts if they are not mentioned explicitly. One of the problems that arise from context is changes in polarity. Look at the following responses to a survey: Everything about it. Absolutely nothing! Imagine the responses above come from answers to the question What did you like about the event? The first response would be positive and the second one would be negative, right? Now, imagine the responses come from answers to the question What did you DISlike about the event? The negative in the question will make sentiment analysis change altogether. A good deal of pre-processing or post-processing will be needed if we are to take into account at least part of the context in which texts were produced. However, how to preprocess or post-process data in order to capture the bits of context that will help analyse sentiment is not straightforward. Irony and Sarcasm When it comes to irony and sarcasm, people express their negative sentiments using positive words, which can be difficult for machines to detect without having a thorough understanding of the context of the situation in which a feeling was expressed. For example, look at some possible answers to the question, Did you enjoy your shopping experience with us? Yeah, sure. So smooth! Not one, but many! What sentiment would you assign to the responses above? The first response with an exclamation mark could be negative, right? The problem is there is no textual cue that will help a machine learn, or at least question that sentiment since yeah and sure often belong to positive or neutral texts. How about the second response? In this context, sentiment is positive, but we’re sure you can come up with many different contexts in which the same response can express negative sentiment. Comparisons How to treat comparisons in sentiment analysis is another challenge worth tackling. Look at the texts below: This product is second to none. This is better than older tools. This is better than nothing. The first comparison doesn’t need any contextual clues to be classified correctly. It’s clear that it’s positive. The second and third texts are a little more difficult to classify, though. Would you classify them as neutral, positive, or even negative? Once again, context can make a difference. For example, if the ‘older tools’ in the second text were considered useless, then the second text is pretty similar to the third text. Emojis There are two types of emojis according to Guibon et al.. Western emojis (e.g. :D) are encoded in only one or two characters, whereas Eastern emojis (e.g. ¯ \ (ツ) / ¯) are a longer combination of characters of a vertical nature. Emojis play an important role in the sentiment of texts, particularly in tweets. You’ll need to pay special attention to character-level, as well as word-level, when performing sentiment analysis on tweets. A lot of preprocessing might also be needed. For example, you might want to preprocess social media content and transform both Western and Eastern emojis into tokens and whitelist them (i.e. always take them as a feature for classification purposes) in order to help improve sentiment analysis performance. Here’s a quite comprehensive list of emojis and their unicode characters that may come in handy when preprocessing. Defining Neutral Defining what we mean by neutral is another challenge to tackle in order to perform accurate sentiment analysis. As in all classification problems, defining your categories -and, in this case, the neutral tag- is one of the most important parts of the problem. What you mean by neutral, positive, or negative does matter when you train sentiment analysis models. Since tagging data requires that tagging criteria be consistent, a good definition of the problem is a must. Here are some ideas to help you identify and define neutral texts: Objective texts. So called objective texts do not contain explicit sentiments, so you should include those texts into the neutral category. Irrelevant information. If you haven’t preprocessed your data to filter out irrelevant information, you can tag it neutral. However, be careful! Only do this if you know how this could affect overall performance. Sometimes, you will be adding noise to your classifier and performance could get worse. Texts containing wishes. Some wishes like, I wish the product had more integrations are generally neutral. However, those including comparisons like, I wish the product were better are pretty difficult to categorise Human Annotator Accuracy Sentiment analysis is a tremendously difficult task even for humans. On average, inter-annotator agreement (a measure of how well two (or more) human labelers can make the same annotation decision) is pretty low when it comes to sentiment analysis. And since machines learn from labeled data, sentiment analysis classifiers might not be as precise as other types of classifiers.

Hubshield - Abusive or Problematic Content Categories - The currently supported types are: Personal_attack - an insult / attack on the addressee, e.g. an instance of cyberbullying. Please note that an attack on a post or a point, or just negative sentiment is not the same as an insult. The line may be blurred at times. Bigotry - hate speech aimed at one of the protected classes. The hate speech detected is not just racial slurs, but, generally, hostile statements aimed at the group as a whole Profanity - profane language, regardless of the intent Sexual_advances - welcome or unwelcome attempts to gain some sort of sexual favour or gratification Criminal_activity - attempts to sell or procure restricted items, criminal services, issuing death threats, and so on External_contact - attempts to establish contact or payment via external means of communication, e.g. phone, email, instant messaging (may violate the rules in certain communities, e.g. gig economy portals, e-commerce portals) Adult_only - activities restricted for minors (e.g. consumption of alcohol) Mental_issues - content indicative of suicidal thoughts or depression Spam - (RESERVED) spam content Generic - undefined

All content uploaded to a community is scanned and analysed for potentially harmful content. Once scanned it is put into a number of categories (or Tagged) for classification. Some of which are explained here. Tags Explained Hateful - Content analysed is hateful. Noise - Content analysed is "unnecessary noise" (spam, ads, scam...). Insult - Text that offends, that hurts someone's dignity. Threat - Text indicating an intention to harm someone, to make them do something against their will. Trolling - Text that aims to create controversy no matter the topic of the conversation; that looks to pollute in particular through disrupting the discussion space. Body Shaming - Text that subjects someone to criticism, ridicule or mockery for supposed bodily faults or imperfections. Racism - Text depicting a belief that race, skin colour, language, nationality, national or ethnical origins justifies contempt for a person or group of people. Hatred - Text demonstrating an extreme intolerance towards a person or group of people. Homophobia - Text describing a prejudice-based intolerance towards homosexuality, gays, lesbians, bisexuals. Sexual Harassment - Text depicting harassment of sexual nature. Moral Harassment - Text meant to annoy someone, to intimidate or humiliate them, with the purpose of degrading someone's life through targeting their physical or mental health. Misogyny - Text expressing hatred of, or prejudice against women or girls. It relates to sexism, promoting an inferior status for women and rewarding those who accept it. Supportive - Text identified as supportive. Neutral - Text identified is not hateful. Ads - Text identified as ads, promotion. Useless - Text is useless, adds no value to the conversation. Link - Text containing links. Scam - Text indicating a scam. Spam - Text that is spam. These Tags or Categories allow Hubshield to determine if the content uploaded is suitable or not. If it's found to be harmful or not suitable for the community the content is rejected before it is published and the person who posted it is is notified. If it's the first time someone has had content rejected then they are given a chance to access the content, rewrite and upload again.

Can Hubshield detect sarcasm? This question started popping right after the bloggers got tired of “can it handle idioms like ‘rain cats and dogs’” and “but does it work with ‘time flies like an arrow, fruit flies like a banana’”. A better question is, “can sarcasm be detected from an utterance alone?” In brief, while some sarcasm can be detected linguistically, most instances of sarcasm rely on expert knowledge, such as knowledge about a situation or/and the mindset of the originator of the utterance (some people are always serious, others are never serious…). A simple example: a sports team loses, and someone posts on their Facebook page, “great game!”, or, a comment to a video from the infamous “Citizen Kane of bad movies”, The Room, says, “incredible acting”; it’s clearly sarcasm, but will you know it from the utterance alone? No. If we were to generalise what sarcasm is on a conceptual level, it is generally a juxtaposition of positivity and negativity. Sometimes, both are present in the utterance (“how are you?” “My house burned down, my family died, otherwise, I’m good.” or the more trivial cases like “Yeah, right”). More often, the negative is omitted from the utterance. (If it is mentioned explicitly, it is often not as funny.) You may have heard of some studies and experiments to detect sarcasm with machine learning. These experiments merely use similarity to existing patterns, which may be able to sniff out something very similar, but is not generalised and hence can’t be used in real-world applications. It is, however, possible to detect sarcasm in a dialogue by looking at the conversation in general: the originator starts with what appears to be a very positive sentiment, the responses are negative and many. On the practical level, sarcasm is relatively rare when an utterance is disseminated to a broad audience. In the business of detecting abuse, it’s simply irrelevant. Go on, look it up in your favourite stream of social media. (Back in the day some people were saying that machine translation software is useless because it can’t translate Shakespeare flawlessly. The response was that it’s the same as claiming that industrial robots are useless because they can’t dance Swan Lake.) If you’re shopping around for an NLP service / component, and a vendor claims the ability to detect sarcasm, it’s a huge red flag. We recommend additional scrutiny and asking them about how they can handle examples with missing information like those cited above. No, machine learning (at least the variety not involving Harry Potter and a magic wand) does not make up for missing info.

Yes. Hubshield AI can be used to actively protect an existing community that is not been created by the Hubly platform. If you would like to explore this option then please contact the Hubly support Team and we will help you 'connect and protect'.

Yes. You need to access the Hubshield control panel. From there you can use the sliders to change the amount of moderation is done. Please note: Changing the Hubshield AI moderation may require you to upgrade to a ‘paid’ subscription. If you would like to speak to one of the Hubly Team with regards to accessing this please contact us.