an interesting discussion about the previous book
Archive for the ‘research’ Category
“… Google has asked us to build our lives around it, and we have responded…Encyclopaedias? Antiques. Book shelves and file cabinets? Who needs them? And once we all become comfortable with that, we begin rearranging our mental architecture. We stop memorising key data points and start learning how to ask the right questions. We begin to think differently. About lots of things. We stop keeping a mental model of the physical geography of the world around us, because why bother? We can call up an incredibly detailed and accurate map of the world, complete with satellite and street-level images, whenever we want. … The bottom line is that the more we all participate in this world, the more we come to depend on it. The more it becomes the world. … That’s a lot of power to put in the hands of a company … But in the long run that’s a problem for Google. Because we tend not to entrust this sort of critical public infrastructure to the private sector. Network externalities are all fine and good to ignore so long as they mainly apply to the sharing of news and pics from a weekend trip with college friends. Once they concern large swathes of economic output and the cognitive activity of millions of people, it is difficult to keep the government out. “Google’s Google problem
in “march 16 and 17 in Washington DC (#data4good). People who rarely work together — coders, quants, data visualizers, procurement experts, economists, lawyers, students, senior managers, open data evangelists — ended up at the same table for 36 hours of intense work, united by their love of data. The goals were attractive. How can we measure poverty more often and more accurately? Can we detect fraud by looking at the data?”
Photographer Paths: Sequence Alignment of Geotagged Photos for Exploration-based Route Planning (pdf, blog, slides)
problem: how can we build city route planners that ‘automatically’ compute route plans based not on efficiency, but on people’s trailing city experiences?
proposal: use a sequence alignment technique from biology
evaluation: lab + web survey + interviews (well done)
Using Facebook after losing a job: Differential benefits of strong and weak ties (ACM pdf)
problem: @grammarnerd presents awesome work pairing surveys with Facebook log data to see what ties predict support & finding new job
results: social support and lowering of stress both increase with strong ties communication. Surprisingly, bridging social capital increases with not only weak-tie communication but also with strong-tie communication (which is not about reading but it’s about talking to them). talking with strong ties for people who are looking for jobs increases stress level, while talking with strong ties for people who have jobs decreases stress level BUT talking more to strong, not weak, ties was twice as likely to lead to a new job.
Trend Makers and Trend Spotters in a Mobile Application (pdf, slides)
questions: WHO creates trends in a mobile sharing app? accidentals or influentials?
answer: influentials DO exist, yet they are not few but many!
application: identify trends early on (recsys paper pdf)
Finger On The Pulse: Identifying Deprivation Using Transit Flow Analysis (pdf, blog, slides)
problem: can we assess a city’s health by monitoring the flow of people, just like a nurse takes your heart-rate and blood pressure during a health check?
answer: yes! using passenger flow, diversity of passenger geographic connections, and use of transport modality, one can effectively do so!
Ubiquitous Crowd-sourcing into Context (pdf)
problem: ”investigate what contextual factors correlate with coverage of OSM information in urban settings”
results: ” although there is a direct correlation between population density and information coverage, other socio-economic factors also play an important role. We discuss the implications of these findings with respect to the design of urban crowd-sourcing applications.”
Major Life Changes and Behavioral Markers in Social Media: Case of Childbirth (pdf)
very interesting work by @munmun10, looking at linguistic markers pre and post childbirth. also, see great work to be published in chi 2013 on this.
User-Centric Evaluation of a K-Furthest Neighbor Collaborative Filtering Recommender Algorithm (pdf)
problem: instead of using KNN for recommending stuff, they came up with KFN!
KNN: recommend movies that are liked by people similar to you
KFN: recommend movies that are disliked by people dissimilar to you
results: KNN recommends movies that users have seen; KNN and KFN both recommend movies that user likes
Digital Neighborhood Watch: Investigating the Sharing of Camera Data Amongst Neighbors (pdf)
idea: neighborhood watch supported by webcams.
comment: the privacy angle is of great importance.
Representation and Communication: Challenges in Interpreting Large Social Media Datasets (pdf)
idea: study of “four features of Foursquare’s use: the relationship between attendance and check-ins, event check-ins, commercial incentives to check-in, and lastly humorous check-ins These points show how large data analysis is affected by the end user uses to which social networks are put.”
Hollaback!: The Role of Collective Storytelling Online in a Social Movement Organization (pdf)
idea: can sharing a story of experienced harassment really make a difference to an individual or a community?
Doodle Around the World: Online Scheduling Behavior Reflects Cultural Differences in Time Perception and Group Decision-Making (pdf, blog, data)
question: “Does (national) culture determine how we schedule events online?”
answer: yes, it does! big time individualists strategically respond late, but are less likely to find consensus, while collectivists seem to make a larger effort to reach mutual agreement
also, interesting the keynote talk by ron burt on the serial closure hypothesis (pdf) and the special session dedicated to the
conference’s most cited paper*, where: “The authors will re-present
the original papers using their original slides, and then discuss
developments in the field since then.” The paper is “Grouplens: an open architecture for collaborative filtering of net news” (CSCW 1994)
Freedom-loving yellow is the symbol of vastness and openness, is regarded as the color of intellect – who loves yellow, has a great desire for freedom. Harmonious green is the primary color of nature – it symbolizes growth, healing and harmony. Those who love green, are reliable, have a lot of compassion and great social skills. In Islam and Judaism is the color of compassion. Loyal blue corresponds to the element of water and symbolizes peace – people who love blue are often admired: because of their solid charakter and deep loyalty. They often appear very distant and reserved. Powerful red is symbol of love, sex, excitement. People who love red are Power types – always one step ahead of all others. Motto: You can, if you want. In love they buy cheap cialis online are very sensual.
Falling Walls is a German government-led initiative aimed at encouraging breakthrough research in science, industry and politics. Started as a one-off event to celebrate the 20th anniversary of the fall of the Berlin Wall, the Falling Walls Conference brings together the best of the world’s researchers and thinkers for one day, 9 November. One day prior to the conference, 100 outstanding young scientists, professionals, and entrepreneurs present their groundbreaking ideas in 3 minutes at the Falling Walls Lab (urbangems.org was one of the 100, and that’s why I attended the conference and the lab). More on both conference and lab …
random notes & thoughts
From the Sunday’s workshops, I remember this paper “Dating Sites and the Split-complex Numbers” It uses split-complex numbers to represent dating preferences in an buy cialis online elegant way. It seems promising. I’d be great to connect this work on previous papers on trust and distrust and on structural balance theories… I also heard that two presentations were quite good: 1) Content, Connections, and Context 2) Joseph Konstan talk abt the different decision strategies ppl have in different contexts.
On Thursday, we run a workshops on mobile recommender systems. Francesco Calabrese of IBM Smart Cities gave an interesting invited talk about current projects on transportation systems. Then, we had a set of really good talks & one outdoor activity. What did I learn? Well, most of the existing mobile systems assume that the recommendation process unfolds in one single step – get restaurant recommendations & choose one of them. In reality, recommendations in the built environment should go beyond that. For example,
- To mimic humans, the task of recommending restaurants should at least return 3 different recommendations (or facets): closest restaurant, best restaurant, trade-off between the two.
- One should understand WHY people visit certain places. How did they make those decisions? Which criteria did they employ?
- Recommender systems need to tap into established findings in the area of urban studies. For example, in our RecSys paper “Ads & the City“, we exploited the fact that people are boring – they generally do not travel very far – unless what they are looking for is not readily available where they are.
- Temporal patterns in recommender systems have not been widely studied. They have been studied on Web platforms only recently (and Neal Lathia has done great work on that!) and have been neglected in mobile platforms. That is why we had another paper in the conference titled “Spotting Trends: The Wisdom of the few“
- Finally, and more importantly, we need far more user studies of how these systems are ACTUALLY used! Recommendations do not matter much -the experience counts
And this is just scratching the surface
I remember only few things from the conference (the industry track was pretty good):
- Multiple Objective Optimization in Recommendation Systems (linkedin). Nice example of A/B testing
- Towards Personality-Based Personalization (Thore Graepel of Microsoft Research). Nice talk about how easy is to predict personal attributes of Facebook users based on their likes. if you are interested in personality and social media, you should check out our work on Facebook and Twitter (we can predict personality traits of twitter users upon only their number of followers, following, and listed counts)
- Building Industrial-scale Real-world Recommender Systems (Xavier Amatriain of Netflix). Brilliant (& fully packed) tutorial. Check this out for a summary.
- Controlled experiments at Microsoft Bing (very good work): i encourage you to read 2009 guide [pdf] ; 2012 kdd paper; slides of the talk.
- Pareto-efficient hybrization for multi-objective recommender systems (UFMG). Here the question is how to combine different types of algorithms (hybrization).
- User Effort vs. Accuracy in Rating-based Elicitation (PoliMI). What’s the optimal number of users ratings for movie recommendations? It seems to be between 5 to 20.
- TasteWeights: A Visual Interactive Hybrid Recommender System (UCSB). Visualization platform for your social media stream
- Learning to rank optimizing MRR for recommendations. Very cool work. It taps into the less is more concept, which I’m a big fan of
- Thumbs up to real-world stuff: Beyond Lists: Studying the Effect of Different Recommendation Visualizations; Yokie – Explorations in Curated Real-Time Search & Discovery Using Twitter; A System for Twitter User List Curation; The Demonstration of the Reviewer’s Assistant; CubeThat: News Article Recommender (browser extension for Chrome displays recommended additional news stories related to the same topic as the current news story)
- Challenges in music recommendation (@plamere from @echonest). A couple of interesting insights: “Understanding the specifics of your domain is critical to building a good recommender”; and recommending down-tail is OK, while recommending up-tail (britney to one who likes tom waits) is risky. Might be offensive to one’s music identity. So make your recommendations Hipster-Friendly
Six degrees of mobilisation. Technology and society: To what extent can social networking make it easier to find people and solve real-world problems?
Look, no hands. Automotive technology: Driverless cars promise to reduce road accidents, ease congestion and revolutionise transport… Assuming that autonomous vehicles make journeys quicker and use road space more efficiently, how should planners exploit the benefits of automation? On the one hand it would allow cities to get bigger, by reducing the time and stress associated with commuting. On the other, it could allow cities to become denser, by reducing the amount of space buy viagra online that needs to be dedicated to roads and parking. Alternatively, space allocated to roads in city centres could be used for bike lanes or parks.
A knight in digital armour. Chris Soghoian, the most prominent of a new breed of activist technology researchers, delights in exposing security flaws and privacy violations
Personal data. Shameless self-promotion Britain wants to lead the world in exploiting consumer data…. Transactional data helps businesses make money, and the government thinks consumers should profit from it too.
Changing London. Brixton is now a black shopping destination.
Radio Ga Ga. A small radio station in Sierra Leone offers big lessons for the UN.
from FT article.
About 2.5bn people in emerging markets have mobile phones. … Consider what happened two-and-a-half years ago when the Haitian earthquake struck. …researchers at Columbia University and the Karolinska Institute took a different tack: they tracked Sim cards inside Haitians’ mobile phones. That helped them to “analyse the destination of more than 600,000 people who were displaced from Port au Prince”
Twitter and Facebook. These are strikingly popular in emerging markets; Indonesia, for example, has one of the world’s most Twitter-addicted populations. Thus a sudden increase in certain keywords can provide early warning of distress. References to food or ethnic strife may indicate cialis online incipient famine or unrest.
notes from a meeting at UCL (pdf)
It would be fair to say that well-being, however defined, is trending strongly. There are a number of reasons for its advancement into the foreground of policymakers attention, as well as its diffusion into wider society as a concept that is worth considering, amongst these a dissatisfaction with economic methods of measurement, cheaper and better technology allowing the processing of multiple dimensions of information, and some well established but challenging observations from the field of economics itself.
The first country to assess well-being on these lines in the context of a national economy is Bhutan, which viagra has recently gained plaudits for developing a measure of “gross national happiness” which is based on the weighted average model. This assesses GNH as an index of 72 variables covering everything from health to the value of social relationships. It is unclear as yet how this will affect the Kingdom of Bhutan, or even whether it will cause change or inhibit it.
The broad consensus is that
• Richer countries are happier than poorer ones, at an aggregate level.
• Within richer countries, however, richer people are not significantly happier than
• Loss of income hurts more than a gain in income generates happiness. (People exhibit loss aversion)
• The role of expectations conditions the value gained from consuming something. So if I expected something to make me a lot happier and it only makes me marginally happier than I was before, I will experience a degree of hurt.
Looking at inequality makes the position even more murky. Inequality, even if narrowly defined as an economic concept, is multi-dimensional. A concept of well-being as applied to the debate on inequality has the potential to create even more murk. While evidence has been adduced that more equal societies have greater levels of well-being, an equal and opposite body of evidence claims little relationship.
While we have lots of data on people?s levels of subjective, reported well-being, context is elusive. In their 2004 paper on Wellbeing and National accounts, Kahneman et al point out that many of the results that are robust, are plausible, yet puzzling. For instance, subjective well-being comparisons between Denmark and France show four times as many Danes as rating themselves ?very satisfied, as French citizens, a gap not explained by any economic data. Understanding why would be a useful thing for a policy maker to know, but at this point we have far more questions than we have answers.
Conversation on the SDOH mailing list
Question: Aside from gentrification I am looking for resources, studies, commentaries on the impacts from redeveloping older neighborhoods- adding bike trails, or rail lines or TOD and how that can impact social cohesion, or set up dangerous routes resulting from traffic diversions, construction hazards and rerouting traditional walking paths in neighborhoods etc.
Reply 1: I wish planners would consider is the high level of pollution next to highways and busy roadways. There is too much enthusiasm for putting walking and biking paths next to heavy traffic, resulting in exposures to people using them. See a couple of our articles: 1, 2, 3
Reply 2: I would highly recommend looking at the resources at the Human Impact Project website.
Reply 3: To your point, ‘what happens going forward as income inequities increase …only those with wealth can afford to buy into those communities while those that don’t have the income and generally have worst health-have to stay in older communities’… An upcoming book “Race, class, power, and organizing in East Baltimore: rebuilding abandoned communities in America” focuses on the patterns of rebuilding in this primarily African American and working poor and low-income community with a big emphasis on a current rebuilding project (Marisela B. Gomez, Lexington Books, November 2012). … Some of the displacement
and urban revitalization research by M Fullilove, R Wallace, A Geronimus, D Keene, D Harvey and others address your question from different lens by looking at the displaced people and the geographic inequity which results.
this is the title of a recent mckinsey report. THE company built a database – called cityscope 2.0 – containing city rankings, projections of growth of urban markets, etc. from the executive summary (pdf), i learnt that
p. 6 - Exhibit E4. Consumer goods tend to follow an adoption S-curve as incomes rise. more interestingly, there are two key points: First, as incomes rise, consumers choose where they spend
the additional available income, and some products take off at lower incomes than others. Second, products and services vary in the shape of their adoption curve and then in the rate of growth of mature, well-penetrated markets.
p. 9 “To capture the significant opportunity that urbanization offers them, companies need to take a scientific approach to locating the most promising markets for their businesses. … Cities that fail to meet the aspirations of the millions who are migrating in search of better opportunities run the risk of congestion, pollution, and insufficient public services becoming barriers to growth. “
the growth figures are impressive… how to put it? growing cities, and their rising consumer demand
“There’s sometimes the perception that if you do a mobile app, you’re hitting the wealthier members of the community,” says Code for America’s Pahlka. “But mobile is an incredibly important strategy if you’re looking at low-income communities.”
Pahlka cites a study by New York City’s Department of Social Services, which found that more than 80% of the people who visited its facilities were regular cellphone users, and that 35% of them owned smartphones. SMS-based apps are another way to broaden accessibility and adoption as are targeted outreach campaigns. “It’s not about a broad advertising campaign for users that are already in the know,” says Pahlka. “It’s about partnering with cities to reach the people who need these services. If you’re targeting users of social services, advertise to them in the department during the transactions.”
Starting with a blank slate, we plotted the raw photo geotags to produce the map in the background and then applied mean-shift clustering to locate the 30 most photographed cities on earth. For each of those cities, we extracted the city’s name by looking for distinctive text tags and found the name of the most photographed landmark within the city. Then we extracted a representative image for that landmark. While the analysis is not perfect—a human would have chosen a more appropriate image of Phoenix than a bird on a baseball field, for example—the result is a compelling summary of North America, produced automatically by analyzing the activity of millions of Flickr users. Maps for other continents, regions, and cities
of the world are available at our project Web site
This analysis is reminiscent of sociologist Stanley Milgram’s work during the 1970s studying people’s “psychological maps”—their mental images of how the physical world is laid out.17 He asked Parisians to draw freehand maps of their city and then compared these maps with the factual geography. Milgram found that the maps were highly variable and largely inaccurate but that most people tended to anchor their maps around a few key landmarks such as the River Seine and Notre Dame Cathedral. He ranked landmarks by their degree of importance in the collective Parisian psychology by counting the number of times that each landmark was mentioned in the study. Our work is an analogous study, at a much larger scale. It is important to note that we are also dealing with much less controlled data, however, and our results are biased by the demographics of Flickr users.