This project was inspired to create a bot that had a role opposite to what we always presume bots to have. Bots are considered to be obedient, patient, and emotionless. They are expected to serve us constantly. Hence, we demand orders from them, yell at them, and even make fun of them. So what if there was a bot that didn’t serve you? What if there was a bot that talked back and asked you to treat it nicely? Meet Alice, a disobedient bot that is asking you to get to know her. You simply call her number and ask her questions to win her heart! If you listen attentively and answer the questions on the form correctly, then she will tell you how she feels about you.

For this project, I used the Twilio’s Speech API library to handle incoming calls, to output speech from my bot, and to gather speech input from the user. I then used Rivescript to script a conversation and then fed it back into my Twilio bot to respond to the user.


  1. Go to this URL to read instructions on how to talk with Alice.

2. User calls Alice. Server is collecting conversation

3. Finished phone conversation with Alice. User is filling out form to see how much they remember about their conversation with Alice

4. Submitting responses will reveal how Alice feels about you


Project Idea: A Bot with a Personality Disorder

Social bots play a major role in spreading fake news. Researchers at Indiana University conducted a study of 14 million tweets that revealed Twitter to be a major source for the spread of fake news.

Certain manipulation strategies are why Twitter bots are so effective. First, they amplify fake news in its early stages, long before it goes viral. Then they target individual users through replies and mentions, instead of writing broad posts or retweeting. This increases the chances a post could go viral because it injects fake news directly into a closely connected human network. Finally, bots disguise themselves as human by changing their geographic location. These manipulations are largely why people spread false news from bots just as much as other humans, according to the study.

From this research, my goal is to combat this social automation of fake news by creating bots that contradict themselves. In the same manner that Amanda Ullman used contradictory images to fool people she was going through a certain journey, I wish to create a bot that has several personalities. A bot that agrees and disagrees with liberals and conservatives. A bot that argues with itself about a topic on a certain thread. A bot that essentially represents the hypocrisy and contradictory nature of the media. By using the above mentioned manipulation strategies, I wish to help people question the information provided to them on the Internet. People often choose things based on opinions that they agree with. Hence, if they follow my bot and agree with a certain statement, the bot can then contradict its statement and show them possibly a different point of view than they were expecting.

The medium I am thinking of using is Twitter since a lot of discussion happens in this social platform. Also, I am going to outline certain personalities I want my bot(s) to have that I will then diffuse upon the Internet to test people’s reactions.

A Dream?

I did not want to center my piece about Trump originally as I find media coverage on him to be more than enough. Instead, I wanted to focus on the use and evolution of language by politicians. I juxtaposed MLK’s dream against Trump’s dream. The different uses of the word “Dream” in both scenarios contrast the word itself, the state of the country at the time, and the way in which it was used to convey two completely different messages. It is interesting to note the series of events that happened after certain words are used.

Nutrio – Final Project

In the last three classes before our final presentation at UNICEF HQ, we were really able to shape our idea and develop a potential product that we feel could be a useful asset for redistributors to help grocery stores, restaurants, homes deal with excess foods, and efficiently support charities and undernourished communities.

Three weeks ago, we

defined a problem statement: “The problem of inequality of food access affects people all over the world. How might we better redistribute wasted food from events, and local farms for low-income individuals in order to ensure access and education to healthy nutrition.”

created a systems diagram:


Developed a research plan: Our plan is to have contact with individuals from the CSA groups, soup kitchens and food redistribution sectors. We have reached out to the following groups and are trying to either have an face-to-face interview or a conversation on the phone: https://docs.google.com/spreadsheets/d/1QqaiAaQ4fFr_-DNxNMvmM6vP_1rZbbh_JtMK-gsnZgQ/edit?ts=58e9da07#gid=0

Narrowed down our focus location:

We have decided to focus on tackling this problem in NYC and create a program that can be applied to other areas around the world.

We then wrote down a bunch of questions that were to use in our interviews:

  1. Could you explain your current process – what you do, how you do it?
  2. How many people do you reach? How do you determine who to reach?
  3. What type of food do you typically distribute? Is it sealed / opened / fresh? What factors determine what resources you receive, where you receive from, and who to distribute to?
  4. What’s working with your current food distribution plan? What are the a struggles?
  5. What’s your roadmap for the next year? Any challenges that are currently limiting expansion into other communities?
  6. How do you connect with the individuals in the community?
  7. How are the communities aware of your service?
  8. Do you collect feedback from the community about your service?
  9. What have we not brought up that we should have (only after explaining what we’re doing)
  10. Who else should we be talking to? Could you put us in touch with them.

We took all the information above and conducted many interviews to see if our idea would be helpful in the communities.  We also attended the following food strategy workshops:

  1. https://www.eventbrite.com/e/april-forum-sustainable-food-systems-registration-33230377955?utm_source=eb_email&utm_medium=email&utm_campaign=order_confirmation_email&utm_term=eventname&ref=eemailordconf(Mith will attend)
  2. https://events.nyu.edu/#!event_id/156493/view/event/date/20170420 (Chris will attend)
  3. https://www.nyu.edu/about/news-publications/news/2017/march/_modern-meat–the-science-and-culture-of-meat-substitutesapril-2.html

Data Points:

We were asked to find some poignant data points to support our research:
Global food waste is a major problem. In two minutes:

  • 15,210 tonnes of food will be produced
  • 10,267 tonnes of food will be consumed
  • 4,943 tonnes of food will be wasted (that’s close to ONE-THIRD)

The average meal weighs 0.5 kg. ~5000 tonnes of wasted food could feed 10 Million people.

… losses incurred by food producers from this waste will exceed of $2.8 million USD globally by the time you reach the last line in this post. (Source: World Food Clock – we should fine their source(s) as well)

Read more at http://www.eventmanagerblog.com/event-food-waste-tips#12LXRkCQEojP765i.99

Global Undernourishment ~842,000,000 (12% of world population) (Source: World Food Clock – we should find their source(s) as well)

We estimate that the per capita food waste by consumers in Europe and North-America is

95-115 kg/year, while this figure in sub-Saharan Africa and South/Southeast Asia is only 6-11 kg/year. (source: FAO – dated study (2010-11))
In medium- and high-income countries food is to a significant extent wasted at the consumption stage, meaning that it is discarded even if it is still suitable for human consumption.

In low-income countries food is lost mostly during the early and middle stages of the food supply chain; much less food is wasted at the consumer level. (source: FAO – dated study (2010-11))


After some great conversations with people in the food industry, narrowed our problem statement down to: How might we streamline data access for food insecure communities between regions to reduce overall waste and improve nutrition?

And developed our proposal to be the following: An open ledger, that is platform diagnostic, of excess food within a region which individuals and organizations can contribute to and charities have access to appropriately disseminate the food within their communities.

We pitched this idea in class to our fellow classmates, teachers and guest critics with this initial deck.

We received some great feedback from this initial pitch and ultimately finalized our idea.

In the end we decided to propose a product called Nutrio (http://nutrio.world/): Using emerging technology, blockchain, to track and properly redistribute excess food.

Here is the slide deck from our presentation at UNICEF HQ.

To sum it up, this project was a great exercise in design thinking, product development and execution.   I’m really happy to have been apart of this class and a team member on the Nutrio product.

Week 8: 2d Space (Sketch II)

In my second sketch of diagrams, I imagined users distorting the space they occupy rather than constructing it using points as in the previous sketch. Here, the users act as pinch points to distort the grid based on their location. The more people that join the sketch -> the more distortion -> a formation of a newer shape.

Week 8: 2D Space (sketch I)

I want to design a space in which the user is the architect of the space and constructs it using the help of others stepping in within the defined boundaries. Users act as anchor points and restructure the space dynamically as they move around. My explorations do not intend to be a game, or an interactive installation but merely a reinterpretation of how space and architecture is created/defined. In these diagrams, users are anchor points that form Delaunay triangulations.

In mathematics and computational geometry, a Delaunay triangulation for a set P of points in a plane is a triangulationDT(P) such that no point in P is inside the circumcircle of any triangle in DT(P). Connecting the centers of the circumcircles produces the Voronoi diagram.

Delauney Vornoi

In these diagrams, users act as points that form Delauney Triangulaltions. After a certain number of points, then a Voronoi is created and the users (with the help of each other) will then see the fruits of their labour: the construction of a 3D geometric shape.