Whom to follow on Mastodon? (Presented at the Dutch-Belgian Information Retrieval workshop in Leiden.)

djoerdhiemstra.com/2018/whom-t

Final grades and extensive feedback for is now available on Canvas. Let me know if you want to discuss your paper.

Students who received a grade of 9: I invite you to send the paper to a workshop, if you are willing to use the feedback to improve the paper. If the paper is accepted, the university will cover costs of travel to, and participation in, the workshop. Please contact me if you would like to submit.

Happy holidays everybody.

students and groups were by mistake removed by the Canvas team. Things are fixed now. Let me know if you still miss anything.

tips for the Conclusion Section:

* State the most important outcome of your work. (Do not simply summarize the points already made in the body. Instead, interpret your findings at a higher level of abstraction).
* Show whether, or to what extent, you succeeded in addressing the need stated in the Introduction.
* Explain what your findings mean to readers. Make the Conclusion interesting and memorable for them. (Do not focus on yourself. for example, by restating everything you did).

tips: Section 2 of the paper:

* Explain the choices you made in your experimental procedure (What justifies using the: a) data sampling strategy, b) recommendation algorithm, c) evaluation approach?)
* If you use a standard or usual procedure, mention that too and provide a citation
* What is special, unexpected, or different in your approach? (Mention this early in your paragraph, ideally in the first sentence)
* Consider using a itemized list, a table or perhaps a schematic diagram

The new deadline for the final paper is Friday 29 June.

Lessons for Assignment 7b: Section 3 of your paper:
* Results, not the process (do not force your readers to go through everything you went through in chronological order.)
* Message of each paragraph upfront (Convey in the first sentence what you want readers to remember from the paragraph as a whole.)
* Focus on what happened, not on the fact that you observed it.
* Include only the information you think you need to convince your audience.
* Summarize results in a table or graph.

Today at the meeting, we discussed the Mastodon rebellion. Interestingly, no one in the class room thought about possible harmful effects of the trending topics feature before... (or search for that matter ) However, after the discussion, most students realized that the features we are developing can have a severe negative impact on vulnerable people on-line.

Some (mostly positive ⭐⭐⭐⭐) feedback on this week's presentations is now on Canvas. I hope to see everyone again next Monday. Have a nice weekend.

There's more feedback for the writing assignments on Canvas, y'all

Program , 28 May, 10:45h. in HB 2C

: Sensing Trending topics in Twitter - Aiello et al.
: Understanding Graph Sampling Algorithms... - Wang et al.
: Local Algorithms for Finding... - Brautbar & Kearns
: Sampling from Large Graphs - Leskovec & Faloutsos
: Friend Finding In Federated Social Networks - Dhekane and Vibber
: Who to Follow Service at Twitter - Gupta et al.
: Link Prediction in Multi-modal Social Networks - Symeonidis & Perentis

I provided feedback for Assignment 3c on Canvas. Let's call it a day. Good night! 🌔

Show more
Mastodon U. Twente

A social network for the University of Twente community. Anyone with an @utwente.nl or @*.utwente.nl email address can create an account here and participate in the global fediverse with millions of other users. This means that students, staff and alumni can create an account here. Content does not reflect the opinions or policies of the University of Twente.
-
We support \( \LaTeX \) formulas: Use \( and \) for inline LaTeX formulas, and \[ and \] for display mode.