What kind of Analysis can be made from User Generated Content

User Generated Content term is given to the text which is published by regular users of internet. People tend to provide or share their ideas/ viewpoints which help them to interact with other people who have similar thought process.

Some websites are two way like Facebook which let users to link with each other and few work on tree principle one following other and is often under one-way category such as twitter.


People are keen to share and post new topics for discussion, philosophical suggestions, news and articles. This describe their mindset and hence human behavior. When human behavior from a specific location at a specific time gets collected, then together they represent pattern of city.

People tend to share information in form of videos as in Youtube, blogs as in blogger, images as in Instagram or Sina Weibo and a lot more.
  • Thus, Multimodal analysis can be good area of research
Analysis made on this type of data provides useful insights for business specific data. 

As per B2B research 2015, 86% of businesses now use content marketing and of those, 70% are creating more content than they did a year ago.

In 2016, small business are looking forward for marketing via Twitter, Facebook, PInterest and other social media websites

Some important tricks which can help in creating useful insights is by marketing
  • Using channel of Youtube and embedding the brand name in domestic videos.
  • Using Whatsapp broadcasting to forward new initiative using viral video/ audio
  • Using catchy names and memes
  • Using viral online spread to those locations at which people are not discussing about your brand.
Using insights, you can target
  • Those locations where people are in search of products and services which you provide
  • Those locations where people are not happy with your competitors.

If you possess product based firm, create something useful for society. The new idea for product will come from
  • General visits to local malls and what people need.
    • Eg. People need to do online shopping where they can receive their products within few hours or may be minutes. Trust factor of local stores is important which should be digital
  • New demands of people
    • Eg. Vedicline beauty products beauty treatment are usually not available at local beauty parlors, You can have startup with something herbal and all natural product based parlor where you can order some natural herbs or may be bring from original plants etc.
  • Visitor may not know where he can get pizza at nearest checkin point, so comes zomato. But how about lock breaker, nearest store for candles, for safety pins etc which you may need anytime.
  • There can be ample of business ideas which you can copy from big cities like those of New York etc which is not available in current market
All these ideas can be obtained from User Generated Content which can be examined using different toolkit. People tend to discuss many such thing which can lead to new business idea.

For better marketing using user generated data, following tricks can be used:
  • Use proper nomenclature for #HashTag
  • Use proper naming conventions for #AtMentions
  • Use URLs
  • Use Images and Video links to emphasize.
  • Follow interesting users and popular users.
  • Carry out discussions using your public profile as much as you can



Comments

Post a Comment

Popular posts from this blog

Analysis and Research trends using Word Co-occurrence Network

Image
Co-occurrence networks   are basically used to provide and give a graphic visualization of potential relationships between people, community, organizations, concepts or other entities represented within the form of written material. The generation and visualization of   co-occurrence   networks has become practical with the advent of electronically stored and save the text amenable to   text mining . By way of definition, co-occurrence networks are the collective interconnection of terms based on their paired presence within a specified unit of text. Networks are generated by connecting pairs of terms using a set of criteria defining co-occurrence. For example, terms A and B may be said to “co-occur” if they both appear in a particular article. Another article may contain terms B and C. Linking A to B and B to C creates a co-occurrence network of these three terms. Rules to define co-occurrence within a   text corpus   can be set according to desired criteria. For example, more str
Read more

Significance of Woman in Data Science

Image
Research scientists, regardless of gender, are doing great in this field. This has been evidenced by a great conference " Global Women in Data Science " hosted by Stanford University (livestream) for 75+ locations all over the world on 3rd February 2017. Many talented academic researchers and practitioners have successful connected to make their dreams and goals burst into reality. It has been sponsored by Microsoft, Google, WalmartLabs, SAP and many more A Grade firms.  Fig 1: Global Women in Data Science Another great initiative, Women in Machine Learning   has been hosted on Facebook. Many female potential researchers join hands for research in machine learning. Many of them have achieved great milestones and many are still on the way.  The world is full of talented, successful and fantastic female speakers Women in Machine Learning and Data science are often un-noticable by traditional recruiters and we can turn it down. Another initiative at Meetup.c
Read more

Different types of clustering for textual documents

Clustering Model 1: Nearest Neighbour Algorithms: KD-Trees and Locality Sensitive Hashing Core Machine Learning Concepts: Distance Metrics and Approximation Algorithms Problem Domain: Finding similar documents Nearest neighbour: Find distance between all other documents and query document. Retrieve the document which is closest Critical Component Document Representation Computing Distances Scaling to large dataset: KD Trees - Not appropriate for very high dimensional documents Thus, Locality sensitive hashing is used for approximate nearest neighbour search. Clustering Model 2: Capturing uncertainty in clustering: Mixture Models Any document can be related to t i topic by x%. Can learn users topic preferences Making soft assignments to clusters -Expectation Maximization Clustering Model 3: Latent dirichlet allocation Mixed membership Probability of words in vocabulary Unsupervised learning task
Read more