Posts tagged review
Mining big data for performance clues as a study guide
Jan 21st
forgetting with personalized content review
Computer software similar to that used by online retailers to recommend products to a shopper can help students remember the content they’ve studied, according to a new study by the University of Colorado Boulder.
The software, created by computer scientists at CU-Boulder’s Institute for Cognitive Science, works by tapping a database of past student performance to suggest what material an individual student most needs to review.
For example, the software might know that a student who forgot one particular concept but remembered another three weeks after initially learning them is likely to need to review a third concept six weeks after it was taught. When a student who fits that profile uses the software, the computer can pull up the most useful review questions.
“If you have two students with similar study histories for specific material, and one student couldn’t recall the answer, it’s a reasonable predictor that the other student won’t be able to either, especially when you take into consideration the different abilities of the two students,” said CU-Boulder Professor Michael Mozer, senior author of the study published in the journal Psychological Science.
The process of combing “big data” for performance clues is similar to strategies used by e-commerce sites, Mozer said.
“They know what you browsed and didn’t buy and what you browsed and bought,” Mozer said. “They measure your similarity to other people and use purchases of similar people to predict what you might want to buy. If you substitute ‘buying’ with ‘recalling,’ it’s the same thing.”
The program is rooted in theories that psychologists have developed about the nature of forgetting. Researchers know that knowledge—whether of facts, concepts or skills—slips away without review, and that spacing the review out over time is crucial to obtaining robust and durable memories.
Still, it’s uncommon for students to do the kind of extended review that favors long-term retention. Students typically review material that was presented only in the most recent unit or chapter—often in preparation for a quiz—without reviewing previous units or chapters at the same time.
This leads to rapid forgetting, even for the most motivated learners, Mozer said. For example, a recent study found that medical students forget roughly 25 to 35 percent of basic science knowledge after one year and more than 50 percent by the next year.
Over the last decade, Mozer has worked with University of California, San Diego, psychologist Harold Pashler, also a co-author of the new study, to create a computer model that could predict how spaced review affects memory. The new computer program described in the study is an effort to make practical use of that model.
Robert Lindsey, a CU-Boulder doctoral student collaborating with Mozer, built the personalized review program and then tested it in a middle school Spanish class.
For the study, Lindsey and Mozer divided the material students were learning into three groups. For material in a “massed” group, the students were drilled only on the current chapter. For material in a “generic-spaced” group, the students were drilled on the most recent two chapters. For material in a “personalized-spaced” group, the algorithm determined what material from the entire semester each student would benefit most from reviewing.
In a cumulative test taken a month after the semester’s end, personalized-spaced review boosted remembering by 16.5 percent over massed study and by 10 percent over generic-spaced review.
In a follow-up experiment, Mozer and his colleagues compared their personalized review program to a program that randomly quizzes students on all units that have been covered so far. Preliminary results show that the personalized program also outperforms random reviews of all past material.
So far, the program has been tested only in foreign language classes, but Mozer believes the program could be helpful for improving retention in a wide range of disciplines, including math skills.
It’s not necessary to have a prior database of student behavior to implement the personalized review program. Students can begin by using the program as a traditional review tool that asks random questions, and as students answer, the computer begins to search for patterns in the answers. “It doesn’t take long to get lots and lots of data,” Mozer said.
The research was funded by the National Science Foundation and the McDonnell Foundation.
-CU-
Buffs wallop Charleston Southern 43-10
Oct 19th
Game Story by B.G. Brooks CUBuffs.com contributing editor
BOULDER – Stepping away from their Pac-12 Conference schedule on a perfect mid-October Saturday, the Colorado Buffaloes eventually stepped out of Folsom Field with a 43-10 romp past overmatched Charleston Southern.
The Buffs’ Big Stepper was tailback Michael Adkins II.
Adkins, a true freshman from San Diego, accounted for a freshman school record four touchdowns on runs of 23, 5, 33 yards and 34 yards. Entering Saturday’s game, the Buffs had scored one rushing TD in their previous five games.
“We always say we want to be about 50-50 (run-pass), it depends on how the game goes,” said Adkins, who finished with 137 yards on 13 carries. “But running today definitely was a factor.”
And how. Tailback/fullback Christian Powell also scored on a 2-yard run as the Buffs enjoyed their most productive running afternoon of the season (218 yards). Adkins’ four TDs eclipsed the school freshman record set by Herschel Troutman in 1994 and equaled by Powell last season.
The Buffs’ top rushing effort this season had been 154 yards in a 44-17 loss at Oregon State. In the two games before Saturday, they had totaled 94 yards against Oregon and 99 against Arizona State. Adkins’ carries had steadily risen in the three previous games, with his 98 yards on 14 attempts at OSU the previous high mark for a CU back this season.
“My carries have been increasing every week so I just took advantage of the carries I got,” Adkins said. “Our line blocked well and I just kept grinding and kept finding the holes . . . it gave me a lot of confidence. I didn’t score in my first two games, so scoring today gives me a lot of confidence moving forward.”
The Buffs broke a three-game losing streak, evened their record at 3-3 and won their first game under first-time starting quarterback Sefo Liufau. CU returns to Pac-12 competition and remain at home next weekend, hosting Arizona (6 p.m., Pac-12 Network) in a game that suddenly looms as perhaps the schedule’s most pivotal.
With Saturday’s win, CU’s goal now becomes to win its first Pac-12 game under first-year coach Mike MacIntyre next week and exit October 4-3 overall. That leaves five conference games in the season’s final month for the Buffs to get two wins and reach six for bowl qualification – something that hasn’t happened since the 2006 season.
“If we get the one next week,” said MacIntyre, “it means November matters in Colorado.”
A true freshman from Tacoma, Wash., Liufau made his college debut last weekend at Arizona State, replacing junior Connor Wood in the first quarter of CU’s 54-13 loss. Liufau finished 18-of-26 for 169 yards and a touchdown, with two interceptions, in that game.
In his first start Saturday, he was 14-of-20 for 198 yards. Liufau’s TD pass covered 60 yards, most of them courtesy of fleet junior Paul Richardson in the second quarter. Richardson finished with eight receptions for 122 yards.
“It feels good,” Liufau said of his home debut and first start. “It was fun being out there with the guys and just playing and having fun.” He called he confidence gained from the win “a tribute to the team – the O-line blocking, the receivers running the routes. Paul had a great play there . . . I definitely got confidence as I kept going.”
The game against previously unbeaten CSU, the FCS’ No. 24-ranked team, was arranged last month to replace Fresno State on the CU schedule. The Fresno State contest was postponed due to the mid-September floods that ravaged Boulder and Boulder County.
“I’m thankful that Charleston Southern wanted to play us,” MacIntyre said. “Or we couldn’t have played today.”
CSU, which entered the afternoon 7-0, was without its first two quarterbacks and started freshman Kyle Copeland, who was playing in only his third game and had thrown two incompletions in his only two attempts. Copeland’s final passing stats: 7-of-14 for 48 yards, one TD, one interception.
CU outgained CSU 416-196 in total offense, with the Buffs adjusting to the Buccaneers’ option attack and holding them to zero points and 46 total yards in the second half.
“(CU) is just a better team than us,” said CSU coach Jamey Chadwell. “We had seven wins before today and I don’t think that’s going to change. The only difference is that won’t play quite as good of a team. They made some good adjustments during the second half, and as for us, we’re going to keep doing what we do.”
The Buffs got out of the first half with a 22-10 lead largely made possible by a timely fumble recovery by Nate Bonsu and Richardson’s runaway speed.
Bonsu got the loose ball following defensive end Chidera Uzo-Diribe’s strip of CSU quarterback Kyle Copeland at the Buccaneers’ 12-yard line in the second quarter. Two plays later, Adkins took a handoff headed off left tackle, weaved to his right and scored from 5 yards out.
Will Oliver’s PAT staked CU to a 15-3 lead that ballooned to 22-3 after a three-and-out CSU series and a 60-yard pitch-and-catch executed by Liufau and Richardson.
Credit Liufau with keeping the play afloat; he fielded a bouncing center snap, collected himself and spotted Richardson crossing right to left in front of the formation. “P-Rich” took the short pass, reversed his field and outran two Buccaneers in pursuit to the right pylon.
Oliver again kicked the extra point and CU seemed comfortably ahead 22-3. The Buffs had opened the game with a 65-yard, six-play scoring drive, getting 52 yards on the ground – the last 23 by Adkins. They went ahead 8-0 when holder Darragh O’Neill ran for the two-point conference.
But after CU had surged in front 22-3, CSU collected itself for its second 9-plus minute drive of the half – the first ended with a field goal when an apparent TD pass on a well-designed pitch was reviewed and overruled – and scored on a 7-yard Copeland to Colton Korn with six left before intermission.
The disallowed TD proved pivotal. The play initially was reviewed and not overturned, but MacIntyre called a time out to allow another look and said he was told by an official that the ball being bobbled by tight end Nathan Prater was missed on the first look.
Chadwell said he was upset because “they took a time out, they reviewed the play (and) it was fine. Then the other review took an hour. They (officials) didn’t go by their protocol . . . I just felt like it was huge deal momentum-wise, because that could have meant a touchdown for us.”
CU, which was leading 8-0 at the time, finished the half with 164 yards in total offense, while CSU had 150. Liufau attempted only six first-half passes, completing four for 74 yards – Richardson’s long TD was for 60 – and being sacked once. Copeland, playing in only his second game and 0-2 in passing, was five-for-eight for 27 yards and a TD. The Buccaneers controlled the ball for 21:51 to 8:09 in the opening half.
The Buffs scored on their first possession of the second half, opening a 29-10 lead after a 13-play, 64-yard march capped by Christian Powell’s 2-yard run. Exactly 3 minutes later – at 4:11 – Liufau and his offense failed to capitalize on a Jered Bell interception near midfield, and the quarter ended with CU clutching its 19-point lead.
With 11:22 to play, Adkins’ 33-yard jaunt and Oliver’s extra point sent the Buffs comfortably ahead 36-10. Just over 5 minutes later, Adkins broke loose again and broke three tackles en route to his record-setting fourth rushing TD.
Wood replaced Liufau and Tony Jones replaced Adkins with just over 3 minutes remaining, with CU taking possession near its 15-yard line and ending the game near midfield.
Contact: BG.Brooks@Colorado.EDU
[includeme src=”http://c1n.tv/boulder/media/bouldersponsors.html” frameborder=”0″ width=”670″ height=”300″]
A county land-use office to help with rebuilding regulations
Oct 10th
Boulder County, Colo. – The Boulder County Planning Commission and Board of County Commissioners will be considering interim development regulations for homes and other structures damaged or destroyed by the historic rains, mudslides and flooding of September 2013. Two upcoming Public Hearings have been scheduled:
What: Planning Commission Public Hearing
When: Wednesday, October 16, 2013, 4:30 pm
Where: Commissioners’ Hearing Room, third floor, Boulder County Courthouse, 1325 Pearl St., Boulder
What: Board of County Commissioners Public Hearing
When: Wednesday, October 23, 2013, 4:30 pm
Where: Commissioners’ Hearing Room, third floor, Boulder County Courthouse, 1325 Pearl St., Boulder
Boulder County is planning for the need and desire to rebuild quickly and restore the community while implementing measures to protect public safety and investments through hazard mitigation and avoidance.
“The goal is rebuilding resilient communities which can better withstand extreme events and maintain the community fabric of these impacted areas,” said Land Use Director Dale Case. “Wise, sustainable rebuilding regulations are a vital part of the recovery process.”
In the aftermath of the unprecedented destruction and the magnitude of extreme weather experienced in September, county staff have closely examined existing regulations dating back to the 1990s and determined that they don’t sufficiently meet public safety standards in all circumstances. For example, current regulations allow property owners to replace structures in some cases without a review and in other cases a review which would require a floodplain development permit which may not adequately address currently known flooding behavior.
Given our community’s recent extreme weather experience, county officials believe is counterproductive for individuals, insurance companies and the public to invest the time, money, and energy into rebuilding in a location that is known to be hazardous.
In many cases the regulations will allow rebuilding to occur within existing lot lines, but require that structures be raised up out of the flood hazard areas or relocated out of hazard areas to a safer location on the property. The current regulations also require structures to be rebuilt at the same height as the old structures. The proposed regulations will allow changes in height to accommodate floodproofing, such as raising the height of the structure to avoid future flood damage.
These interim regulations are proposed to be in effect until April 30, 2014. During this time, property owners can rebuild destroyed or substantially damaged structures in safer locations, in a way that meets the floodplain development requirements (if the new structure is proposed to be located in a floodplain) without going through Site Plan Review. Land Use staff will work with property owners and representatives from other county departments to perform a Hazard Mitigation Review. The goal of this review is to help property owners rebuild in a way that is more resilient to future disasters.
During this interim period staff is committed to reaching out to the communities to understand the needs and issues of residents who are facing complex issues to restore their homes, property and lives. As part of the effort to assist property owners and residents impacted by the flood the county has set up a Flood Recovery Center at the county’s Land Use Department staffed by functional experts in onsite wastewater (septic) systems, floodplain regulations, planning and building code. The center and the county will also pursue other restoration resources and hazard mitigation programs to assist those impacted.
The staff recommendation and proposed regulations have been posted to the Land Use Department’s website(www.bouldercounty.org/property/build/pages/lucodeupdatedc130003.aspx) for public review and comment. Residents are encouraged to read the draft, call us at 720-564-2623 if you have questions, email your comments to planner@bouldercounty.org, attend the upcoming public hearings, and make your opinion known.
[includeme file=”/media/boulderfloodsponsors.txt]