October 1, 2013
Host: Ted Simons
Twitter Analysis of Public Opinion
- Two Arizona State University computer science doctoral students are developing computer models for analytical systems that can gather data generated by Twitter and organize it in a way that can lead to analysis of public opinion. ASU Computer Informatics professor Subbarao Kambhampati will talk about the twitter analysis tools.
- Subbarao Kambhampati - Computer Informatics Professor, Arizona State University
| Keywords: twitter
Ted Simons: ASU computer science doctoral students are working on research to use data from Twitter to gauge and analyze public opinion. ASU computer informatics professor Subbarao Kambhampati is here to talk about it. Welcome.
Subbarao Kambhampati: Thank you.
Ted Simons: Talk to us about using Twitter to analyze public opinion.
Subbarao Kambhampati: I was thinking of a time when people tried to figure out what an event- how is an event actually received by just looking at the town square and what the people in the town square say. Twitter has become the modern day town square. People can get on and start expressing themselves. We were watching the fact that oftentimes, let's say there was presidential debate going on last year, they would look at what people were saying about various, for example, the Big Bird thing became a big issue, for example. One of the questions, there are obviously journalists and some of the time is going to be invested into actually counting which parts of the event are being talked about, which of the tweets, and whether they are positive or negative, rather than going to the higher level. We thought we can use the computer science techniques to support this actual alignment in sentiment analysis. And then the journalists can do more of an interesting analysis of public opinion.
Ted Simons: How do you do a higher level of analysis, get these twitter feeds segmented and fragmented. How are the metrics?
Subbarao Kambhampati: So the way the twitter has hosts, you can get copies of tweets in real time. Of course we are not rich enough to get them, we get a fraction of it, a sample of it. And many of these- the public event in particular, you know that there is a prespecified tag to which people are tweeting. So you do know what tweets are relevant to this particular event. What you don't know is which part of the event are they talking about. For example, something as simple as the shutdown, it's a single-point issue. Something more complicated like an entire debate, something like a speech by Obama, this could have multiple different things going, and you want to be able to see which pieces are being talked about by which of the tweets.
Ted Simons: How do you define what's being said? Twitter has a language all it's own. You have to figure out and align fragmented words, slang words, words that aren't even words.
Subbarao Kambhampati: The thing I'd like to say is the following. If you look at the metaphor of the search engines, when you're looking for something on Google, how could the search engine know the specific query I'm looking for. Mostly they’re doing word-level analysis and trying to show you files. And what's interesting is the sweet spot where the search engine gets you close to something that you're looking for, and then you can go through the documents yourself actually doing an analysis of English. In twitter they only want 45 words and there is lots of slang and so on. What's interesting is because there are so many of them and essentially looking at- it's a public event with a large number of people tweeting. So you can still get, even if you don’t get specific tweets or if you don't get the exact nuance correctly, you will get the sentiment expressed by a large number of people.
Ted Simons: Indeed, a large number of people. But are you getting public opinion in general or public opinion on the twitter-verse? You have to figure out, who are these people tweeting.
Subbarao Kambhampati: I am a computer science professor, I'm not a journalist. What we are not doing here is getting an exact carefully selected sample of people. The work you are doing is not going to redo the careful studies of focus groups, Gallup Polls and so on. They express opinions whether you want it or not. More in journalism, in fact if you look at the "New York Times," many of the events that happen, people lead by saying what was the twitter universe saying. For example, there was like a beauty pageant and somebody from Indian origin won. The interesting thing is that most people probably shrugged about what happened but a few people did get onto the twitter. The media did report it. All we’re saying is that you can support analyzing the self-selected people who watched and what they are saying. If you want to use Twitter to see how a particular public event recieved, we will support it from a technical view.
Ted Simons: Computational science in general, how far can it go to understand human behavior, human thought, human action?
Subbarao Kambhampati: That's one of the most fascinating things that's going on right now in the context of twitter. People wanted you to express their opinions. But since there are so many people expressing opinions at the same time, twitter has had to become a footprint of the human behaviors. It was started some time back, we would know different people in different countries sleep at different times. So these guys would look at the mass of tweets and decide well, this is the times when people are sleeping and these are the times when they are waking up, and so on. Because of the sense of the numbers involved, you do get a good understanding of the footprint of the collective human behavior, not a single person's behavior. I may not know what you are trying to say by your tweet, but for the mass of our audience actually tweeting about this event, I can get a general idea of which topics that were received well.
Ted Simons: So very quickly, response so far to the research.
Subbarao Kambhampati: So one of the interesting things is that we started by looking at- so there are two different aspects from a technical point of view. One is that the tweets are going on and you need to connect to which part of the event they are talking about. There is the alignment work and the sentimental analysis part. So we are focusing on presenting the technical details of this work to the community, not so much of talking to journalists to see if they can do this. This is like a good beginning, I guess.
Ted Simons: Good beginning, good information, good to have you here. Thank you so much for joining us.
Subbarao Kambhampati: Thank you.
Ted Simons: I'm Ted Simons, thank you so much for joining us.
Yarnell Hill Fire Report
- A report was released by the Arizona State Forestry Division on the Yarnell Hill Fire, which killed 19 firefighters. Wildfire expert Jim Paxon, currently of the Arizona Game and Fish Department, will discuss the report.
- Jim Paxon - Wildfire Expert, Arizona Game and Fish Department
| Keywords: yarnell hill fire
, around arizona
Ted Simons: Well, the Arizona State Forestry Division recently released a much anticipated report on the Yarnell Hill fire which killed 19 members of a hotshot firefighting team. Wildfire expert Jim Paxon, currently of the state game and fish department, joins us now to discuss the report. Thanks so much for being here.
Jim Paxon: Thank you for having me, Ted.
Ted Simons: 115 some odd paged document here, your thoughts on the report, what did you learn?
Jim Paxon: I thought it was very even-tempered, written from the perspective of a firefighter. That's pretty unique, it'll go a long way in the future to help firefighters ask questions. I think that's beneficial for the entire firefighting community.
Ted Simons: Was it too even-tempered?
Jim Paxon: No, I don't think so. They did refuse to point fingers. They refused to engage in what they call hindsight bias, which to me is armchair quarterbacking. It's really easy to determine fault from your easy chair.
Ted Simons: Can you though, from the easy chair, with hindsight, look at things maybe more caustically than the report? There's been some criticism of the report that there is no blame here, no answers, just a lot of questions. How do you respond to that?
Jim Paxon: I think they drew some conclusions. What they refused to do is to point a finger of blame where it could not be assessed with facts and with the experience of the Yarnell Hill fire. What they did try to do was go back and reconstruct what that crew did in their last moments and leading from leaving the black all the way down to where they were entrapped.
Ted Simons: Leaving that safe area on the ridge and going into a bowl with up to 10-foot-high fuel. Why? Why did they do this?
Ted Simons: They looked at that. We've seldom seen fire move like that fire did, even with the weather event. I think the conclusion was drawn were the crew thought they had an hour to go a little over a mile. That's doable. In reality, they had less than 20 minutes. Because of the speed of that fire as that weather event came over, and they dropped into that bowl, they lost sight of the fire. And then it came around the bend and it was burning so fast they just couldn't get out of the way.
Ted Simons: There was a two-track road on that ridge, and it's suggested in the report, if they had stayed on that two-track road they would have made to it a ranch, sounds like it's a fortress up there, very well protected. You're saying they probably didn't want that, they wanted to engage.
Jim Paxon: If they had stayed on that road they would have dropped over the ridge away from the fire to highway 89. But the report concludes that they were trying to go to Yarnell to help out because that's where fire was going to put lives and property at risk. So they dropped down through that bowl, kind of a short-cut to try to get there to assist in the firefighting operations.
Ted Simons: Let's talk about radio challenges, the documents mention this and chronicle 30 minutes without contact. What happened there?
Jim Paxon: That's one of the questions we'll never know. It really troubles firefighters, that silence. Understand, too, there's the chaos of fire moving towards people's valley, evacuations there. Three miles away fire is moving towards Yarnell and people are evacuating there. They are trying to reposition resources, get folks in place, do what they can safely, get the residents out of the way, a lot of chaos. The crew was the only crew on the mountain when all this was happening.
Ted Simons: Should they have been the only crew on the mountain?
Jim Paxon: Well, you know, they had an option to stay in the black, and watch the fire go by. Grandstand in the bleachers and watch the fireworks. And the conclusion was they chose to go be part of the trying to help Yarnell out. Should they have moved off the mountain earlier? You know, they had the weather alerts, they realized what was happening, they were in communication that they were moving. It just was not understood that they were moving away from the black and going down through that unburned area.
Ted Simons: It sounds like from the report management thought the crew was still in the safe area.
Jim Paxon: They did.
Ted Simons: And the crew obviously was not. That's where the silence and the radio problems exist. Is there is some sort of- will there be some sort of change in protocol be looked at, where if you're not hearing anything, if you don't hear anything stay put, and if you're management, find out why you're not hearing anything.
Jim Paxon: They will look at communications channels and the outputs and devices, whether they be GPS or some way to track those folks that's going to be examined closely. That's really a national question. But the communications, we have worked on firefighters for years and years, and I started this game back in 1969. Not everybody had radios then. And yet, we went from a 10-code like the police use, to clear text. Now we need to make sure that we understand both sides, what's being communicated. And there probably were some acceptances that messages were sent that weren't meant, or received and not understood. That's problematic and this report identifies that.
Ted Simons: You mention problematic So the document does not, though, seem to show any indication of negligence.
Jim Paxon: No. You know, the incident command, the management and crew all operated within the parameters that are appropriate in the national wildfire coordination. All of our fireline handbooks, incident management practices, they looked at that very closely.
Ted Simons: No reckless actions according to the document.
Jim Paxon: Yes, I'm buying that.
Ted Simons: How come?
Jim Paxon: There was some accusations put out in the public that the crew wasn't qualified and they shouldn't have been there. Totally false. This team looked at their training, qualifications, crew structure, the number of type 1 and type 2 firefighters, they met all the standards. They were current on their training. They had the required days off, they were vindicated that this crew should have been on that fire.
Ted Simons: So this crew was trained enough to be a type 1 team as opposed to a type 2?
Jim Paxon: Absolutely. They were -- they had been on fires, I think on 28 fires in the last two years. This was an excellent crew. They had been on several fires this season. They had been on the docy fire that burned up through Prescott just two weeks before. They were on the Thompson Ridge fire in New Mexico and received excellent commendations for their firefighting.
Ted Simons: Were they due for a rest because of those fires? Were they overworked or exhausted?
Jim Paxon: No, these were the best fit, most energetic young people. The youngest was 21, the oldest was 43, Eric marsh, the crew superintendent. These were tough guys, cross-country skiers and mountain bikers. They are the best of the best. They were day 13 of duty, but they had two days off of fires before. They could have gone two more days before they had to take days off according to our standards. But that's still a guideline. They were within the work risk guidelines. And they were fit to go on this fire.
Ted Simons: There were also concerns, and I heard this from people in that general area up there, that the fire started Friday. And that there was little if any action until things got out of hand. The bottom line for them is it should never have reached this point. Valid?
Jim Paxon: I disagree. You know, on Friday they had five lightning starts, this was one of them, the Yarnell Hill fire. They had clouds overhead. You don't put people on top of a granite knob with lightning up there, and hike them up in the dark through really rough country, and dense chaparral. You wait until daylight the next day, which they did. This fire kind of skunked around. It didn't really do much for a day and a half. Then the evening of 29th it started to burn. As it did, they increased resources. They got a type 2 incident management organization. They called two hotshot crews, order air tankers and helicopters. They did appropriate things for incident management. The whole thing that happened on this fire was that outflow from a thunderstorm that blew this fire up. It was an anomalous event.
Ted Simons: That being said, critics, a variety of critics look at this report and say 19 people died. Someone must have done something wrong. Yet the report does not seem to show that.
Jim Paxon: I think the report highlights that anomalous event and there are some indications that the proper attention wasn't paid to by the crews in the chaos, perhaps tracking the crew was lost that 30 minutes that really troubles a lot of firefighters. There was silence as that crew was moving. I think things will be done differently. But the folks out there, and I know most of them, were doing the dead level best they could with the situation they were dealt. They were doing things that they had experience, that they had training, and that they were trying to do the best for the fire on the ground.
Ted Simons: If they are doing their best and this is the result, does that best change by way of training and by way of guidelines? After the Dude fire, I remember after that, a lot of wildfire training and protocols seemed to change, from a distance it seemed like a lot of things happened because of that fire. Many more people died on this one. Will we see those kinds of changes?
Jim Paxon: One of the recommendations was they could develop a staff ride. This is from the military, after action reviews. Go to the battlefield and see why we either won or lost. We need to do that. And look at the characteristics, the fuels, the rate of spread, the winds, weather, everything. Look at the tactics, learn from it. One of the things that's really neat about this report is they asked questions for the firefighter. What is safe black? How valid is a weather forecast for how long? When do you make the decision that you shouldn't go through green to reach a safety zone? Every firefighter that has experience has run from a fire to get to a safety zone. These kids couldn't run because the fire came around the corner and was in front of them and cut them off.
Ted Simons: I would imagine another area to look at is getting those firefighters to understand that- it sounds like that area, having not been up there, was really a bowl. It would be very difficult to escape something like that. Is there a way, by way of communication, maybe they get GPS devices, I don't know. There has to be a way I would think for future firefighters to not go into such dangerous areas without realizing what's happening around them.
Jim Paxon: I think in the future we'll see more questions asked, particularly about going through unburned fuels, the green we call it, to reach a safe area. There will be more questions asked by management, where are you going, what are you doing, why are you doing that, how can we help you. Another disconnect was that air-tac that was an eye in the sky, ad they had an air supervisor module that was working on retarding airplanes and helicopters. And when air-tac ran out of time, the supervisory module kind of took over and they were doing two things at once. I doubt that we’re going to see that again though. I believe there will be appropriate air resources for this situation in the next fire.
Ted Simons: Does the report reduce the likelihood of something like this happening again?
Jim Paxon: The report emphasizes that firefighting is an inherently risky profession. It does not accept risk that results in fatalities. It does accept that we have to make decisions and we need more information, more criteria, more making sure that those decisions minimize and mitigate risk. That's where the question part of this second part of the report tells firefighters to ask those questions. Don't depend on what somebody else tells you. You ask those questions and make sure what you're doing is safe and will still enable you to fight the fire.
Ted Simons: We have another investigation due by way of the state, correct?
Jim Paxon: That's right. The Arizona Department of Occupational Safety and Health is going to have an investigation. They will look at more of the legal parameters and perhaps some of the training and the things that go more to law, and that's expected to be out before the first of the year.
Ted Simons: We may see another vantage point of the incident by way of that report.
Jim Paxon: I think we will.
Ted Simons: Critics of the report were saying, oh, I knew it would be like this, no one will show blame or cause because they are afraid to or everyone's doing the CYA business. How do you respond to that especially when people are desperate for answers and yet the report raises more questions than provides answers.
Jim Paxon: Many of the answers to those questions died with those 19 brave young men. I don't know that we would in any way be able to answer those questions. But I like this report because it brings to the very forefront of a firefighter's acumen, don't not answer these questions. We need to take looks, long and hard, before we leave safe black and go across green to reach a safe zone. If it means reengaging, is it worth the risk for us to go there to reengage. This is a good report. It was written by firefighters for firefighters.
Ted Simons: And it's a better report if some of those questions are eventually answered.
Jim Paxon: Yes.