This website uses cookies and similar technologies to understand visitors' experiences. By continuing to use this website, you accept our use of cookies and similar technologies,Terms of Use, and Privacy Policy.

This paper talked about results of comparing different machine learning techniques in classification problem. The results are interesting and somehow expected. Support Vector Machines (SVM) and Artificial Neural Networks (ANN) performed best overall. Also, feature selection is a a great factor for any algorithm. Selecting irrelevant features will have a huge impact on any of them and Linear Discriminant Analysis (LDA) suffered most. Apply some sort of filter before using features as it is very important, especially for ...
Hey everyone! METRO (Metropolitan New York Library Council) announced that Code4LibNYC is hosting an event for anyone interested in libraries, coding, and systems/web services! The event is on Wed, Sep. 10, 2014 from 2:00pm - 4:00pm and Eric Glass, a GIS/Metadata Librarian from Columbia, will be discussing topics like geospatial data repositories, ebooks platforms created in Python and Django, social media integration in web development, and more! It's a great op...
1 Comment
I have been exploring the R library qdap recently and it has many functions for doing exploratory analysis for dialogues. Here is something I just found by using the function "question_type" in this library. This function counts the occurrences of different types of questions, such as "where", "why", and "how", in the sentences. I grouped the sentences according to the ratings of the vialogue conversations they belong to. See the plot below for the result. We can make a few interesting conclusions:
Vialogue 16171 talks about the Advanced Placement (AP) courses offered in different high schools which reflects the problem of educational inequality and some possible intervention methods. We applied the hidden topic Markov models on this vialogue. More specifically, we assumed that the comments from an individual post share the same topic and we treated the comments within each timestamps as individual documents. Here is what we found. We used four different colors to represent four different topics: topic 1 is red; topic 2 is gre...
5 years ago
Note: It is a paid software. However, it is FREE for students! Tableau is a drag-and-drop data analytical software that helps individuals create engaging visualizations and comprehensive data dashboards. It is a great tool to understand our products from multiple perspectives such as daily operations, user engagement, and campaign effectiveness. It also benefits researchers by offering a quick prototype of study analysis such as survey outputs. Pros: No coding is needed, though the design of measurement is necessary As long as you have some experien...
5 years ago
Big data has been a big factor in determining representation in our modern world. The social phenomena of big data might change the way we “know” knowledge since with big data we can see the entire world in one picture. However, there are multiple flaws in this approach and Microsoft researcher Kate Crowford points it out in her Vialogues, Hidden Bias of Big Data. First off, the biggest flaw is bias. Data inherently is biased, since the representation of data is determined by who decides to report it as well as who w...
5 years ago
This is a screenshot of the D3 interactive streamgraph of Vialogues 6973, a long (>20 min) video named “anthro of YouTube” with 116 total comments. Please feel free to play with the interactive version of prototype here. It is a visual illustration of concept flows of a discussion for its corresponding video, as it shows the change and switch of discussion concepts along with the video time stream. Only ...
My current research is evaluating topic coherence of discussions and their corresponding videos. Both YouTube and Vialogue discussions are related to the posted videos. However, discussions on YouTube's platform is a forum discussion while Vialogue enables moderated time-stamped discussions. We are trying to research whether on average, the same piece of educational video on the two platforms result in different levels of topic coherence. I am now in the process of solving this problem, and I am fascinated by the approaches. 1) Learn and discover, not reinvent the wheel In the past...