This gist contains Java code for archiving tweets in MongoDB, and R code for retrieving tweets for analysis. Please note that there're a couple of dependencies: (1) You should setup your MongoDB (I used the free plan at https://mongolab.com/); (2) You should have setup your Twitter api (check https://dev.twitter.com/); (3) Java code: include twi…

get_mongo.R

library(rmongodb)

## Host info and credentials
host <- "ds053858.mongolab.com:53858"
username <- "your_username"
password <- "your_pass"
db <- "your_db"

## Connect to mongodb
mongo <- mongo.create(host=host, db=db, 
                      username=username, password=password)

## Get a list of collections within our namespace
#  here I used each collection for a twitter archive
mongo.get.database.collections(mongo, db)

## Create a string that points to the namespace
#  the collection I'm interested in is "#mri13"
collection <- "#mri13"
namespace <- paste(db, collection, sep=".")

## Check the total number of tweets in "#mri13"
mongo.count(mongo, namespace, mongo.bson.empty())

## Build a query to find how many tweets were posted by me
buf <- mongo.bson.buffer.create()
mongo.bson.buffer.append(buf, "user_name", "bodongchen")
query <- mongo.bson.from.buffer(buf)

# get the count
count <- mongo.count(mongo, namespace, query)
count

## Get all tweets posted by me
tweets <- list()
cursor <- mongo.find(mongo, namespace, query)
while (mongo.cursor.next(cursor)) {
  val <- mongo.cursor.value(cursor)
  tweets[[length(tweets)+1]] <- mongo.bson.value(val, "tweet_text")
}
length(tweets)

## Retrieve all tweets and put into a dataframe
library(plyr)
df_arch1 = data.frame(stringsAsFactors = FALSE)
cursor <- mongo.find(mongo, namespace)
while (mongo.cursor.next(cursor)) {
  # iterate and grab the next record
  tmp = mongo.bson.to.list(mongo.cursor.value(cursor))
  # make it a dataframe
  tmp.df = as.data.frame(t(unlist(tmp)), stringsAsFactors = F)
  # bind to the master dataframe
  df_arch1 = rbind.fill(df_arch1, tmp.df)
}
dim(df_arch1)

### Try with another collection
collection2 <- "#edtechchat"
namespace2 <- paste(db, collection2, sep=".")
mongo.count(mongo, namespace2, mongo.bson.empty())

TwitterLoop.java

package twitter_loop;

import com.mongodb.BasicDBObject;
import com.mongodb.DB;
import com.mongodb.DBCollection;
import com.mongodb.DBCursor;
import com.mongodb.Mongo;
import com.mongodb.MongoException;
import java.net.UnknownHostException;
import java.util.List;
import java.util.Scanner;
import twitter4j.Query;
import twitter4j.QueryResult;
import twitter4j.Status;
import twitter4j.Twitter;
import twitter4j.TwitterException;
import twitter4j.TwitterFactory;
import twitter4j.UserMentionEntity;
import twitter4j.conf.ConfigurationBuilder;

public class Twitter_loop {
    
    /**
     * Settings before running the program
     */
    // Mongodb info
    private String host = "ds053858.mongolab.com";
    private int port = 53858;
    private String db_name = "your_db";
    private String username = "your_username";
    private char[] password = "your_password".toCharArray();
    // Twitter api
    private String consumerKey = "yourkey";
    private String consumerSecret = "yoursecret";
    private String accessToken = "yourtoken";
    private String accessTokenSecret = "yourtokensecret";
    // Time interval
    private int seconds = 60;
    // Number of tweets to get each time
    private int count = 100;

    private ConfigurationBuilder cb;
    private DB db;
    private DBCollection items;
    

    /**
     * static block used to construct a connection with tweeter with twitter4j
     * configuration with provided settings. This configuration builder will be
     * used for next search action to fetch the tweets from twitter.com.
     */
    public static void main(String[] args) throws InterruptedException {

        Twitter_loop taskObj = new Twitter_loop();

        taskObj.loadMenu();
    }

    public void loadMenu() throws InterruptedException {
        
        System.out.print("Please choose your Keyword:\t");

        Scanner input = new Scanner(System.in);
        String keyword = input.nextLine();

        connectdb(keyword);

        int i = 0;

        while (i < 1) {
            cb = new ConfigurationBuilder();
            cb.setDebugEnabled(true);
            cb.setOAuthConsumerKey(consumerKey);
            cb.setOAuthConsumerSecret(consumerSecret);
            cb.setOAuthAccessToken(accessToken);
            cb.setOAuthAccessTokenSecret(accessTokenSecret);

            getTweetByQuery(true, keyword);
            cb = null;

            Thread.sleep(seconds * 1000);              // wait
        }
    }

    public void connectdb(String keyword) {
        try {
            // on constructor load initialize MongoDB and load collection
            initMongoDB();
            items = db.getCollection(keyword);

            //make the tweet_ID unique in the database
            BasicDBObject index = new BasicDBObject("tweet_ID", 1);
            items.ensureIndex(index, new BasicDBObject("unique", true));
        } catch (MongoException ex) {
            System.out.println("MongoException :" + ex.getMessage());
        }
    }

    /**
     * initMongoDB been called in constructor so every object creation this
     * initialize MongoDB.
     */
    public void initMongoDB() throws MongoException {
        try {
            System.out.println("Connecting to Mongo DB..");
            Mongo mongo;
//            mongo = new Mongo("127.0.0.1");
//            db = mongo.getDB("tweetDB2");
            mongo = new Mongo(host, port);
            db = mongo.getDB(db_name);
            db.authenticate(username, password);
        } catch (UnknownHostException ex) {
            System.out.println("MongoDB Connection Error :" + ex.getMessage());
        }
    }

    public void getTweetByQuery(boolean loadRecords, String keyword) throws InterruptedException {

        TwitterFactory tf = new TwitterFactory(cb.build());
        Twitter twitter = tf.getInstance();

        if (cb != null) {

            try {
                Query query = new Query(keyword);
                query.setCount(count);
                QueryResult result;
                result = twitter.search(query);
                System.out.println("Getting Tweets...");
                List<Status> tweets = result.getTweets();

                for (Status tweet : tweets) {
                    BasicDBObject basicObj = new BasicDBObject();
                    basicObj.put("user_name", tweet.getUser().getScreenName());
                    basicObj.put("retweet_count", tweet.getRetweetCount());
                    basicObj.put("tweet_followers_count", tweet.getUser().getFollowersCount());
                    basicObj.put("source", tweet.getSource());
                    //basicObj.put("coordinates",tweet.getGeoLocation());

                    UserMentionEntity[] mentioned = tweet.getUserMentionEntities();
                    basicObj.put("tweet_mentioned_count", mentioned.length);
                    basicObj.put("tweet_ID", tweet.getId());
                    basicObj.put("tweet_text", tweet.getText());

                    try {
                        items.insert(basicObj);
                    } catch (Exception e) {
                        System.out.println("MongoDB Connection Error : " + e.getMessage());
                    }
                }

                // Printing fetched records from DB.
                if (loadRecords) {
                    getTweetsRecords();
                }

            } catch (TwitterException te) {
                System.out.println("te.getErrorCode() " + te.getErrorCode());
                System.out.println("te.getExceptionCode() " + te.getExceptionCode());
                System.out.println("te.getStatusCode() " + te.getStatusCode());
                if (te.getStatusCode() == 401) {
                    System.out.println("Twitter Error : \nAuthentication credentials (https://dev.twitter.com/pages/auth) were missing or incorrect.\nEnsure that you have set valid consumer key/secret, access token/secret, and the system clock is in sync.");
                } else {
                    System.out.println("Twitter Error : " + te.getMessage());
                }
            }
        } else {
            System.out.println("MongoDB is not Connected! Please check mongoDB intance running..");
        }
    }

    public void getTweetsRecords() throws InterruptedException {
        BasicDBObject fields = new BasicDBObject("_id", true).append("user_name", true).append("tweet_text", true);
        DBCursor cursor = items.find(new BasicDBObject(), fields);

        while (cursor.hasNext()) {
            System.out.println(cursor.next());
        }
    }
}

Dear dirkchen, I'm currently working on the same code to transfer my data collections of tweets from my MongoDB databases to R to deals with text mining & social network analysis.
I have not understand the conversion of your collection with the function paste () which gave me a NULL result for me.
Anyway, I have a limitation with rmongodb and plyr packages on large tweets collection data sets, and things for me don't want to work properly. I have posted a stack overflow here : http://stackoverflow.com/questions/22445419/transfer-large-mongodb-collections-to-data-frame-in-r-with-rmongodb-and-plyr
Any help would be merely appreciated.

Cyrille